
# os to manipulate files
import os
# Importing pandas to work with DataFrames.
import pandas as pd
# Importing numpy to general methods.
import numpy as np
import time
import datetime
from datetime import datetime, date,timedelta
# Importing the matplotlib to create graphics
import matplotlib 
import matplotlib.pyplot as plt
%matplotlib inline
matplotlib.style.use('ggplot')

# Import seaborn to better the visualization
import seaborn as sns
import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import plotly.express as px


# Scipy for statistics
from scipy import stats
from sklearn.metrics import mean_absolute_error,r2_score
from sklearn.model_selection import train_test_split
from sklearn import linear_model
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from scipy import integrate, optimize

# ML libraries
import lightgbm as lgb
import xgboost as xgb
from xgboost import plot_importance, plot_tree
from sklearn.model_selection import RandomizedSearchCV, GridSearchCV
from sklearn import preprocessing, svm
from sklearn import linear_model
from sklearn.metrics import mean_squared_error,explained_variance_score
import sklearn
import matplotlib.dates as dates
import seaborn as seabornInstance 
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from scipy.stats import zscore
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score
from matplotlib import rcParams
#sns.set()
#sns.set_context('talk')
import warnings
warnings.filterwarnings('ignore')


# We'll download this file using the urlretrieve function from the urllib.request module.
from urllib.request import urlretrieve

urlretrieve('https://covid.ourworldindata.org/data/owid-covid-data.csv','owid-covid-data.csv')

('owid-covid-data.csv', <http.client.HTTPMessage at 0x205adf36f10>)


#Read data from a CSV file into a Pandas DataFrame object
world_covid19_df = pd.read_csv('owid-covid-data.csv')


owidcovidcodebook=pd.read_csv('https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-codebook.csv',index_col=0)


owidcovidcodebook


world_covid19_df


type(world_covid19_df)

pandas.core.frame.DataFrame


#Get the number of rows & columns as a tuple
world_covid19_df.shape

(76215, 59)


#View basic infomation about rows, columns & data types
world_covid19_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 76215 entries, 0 to 76214
Data columns (total 59 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               76215 non-null  object 
 1   continent                              72473 non-null  object 
 2   location                               76215 non-null  object 
 3   date                                   76215 non-null  object 
 4   total_cases                            74913 non-null  float64
 5   new_cases                              74911 non-null  float64
 6   new_cases_smoothed                     73910 non-null  float64
 7   total_deaths                           65624 non-null  float64
 8   new_deaths                             65782 non-null  float64
 9   new_deaths_smoothed                    73910 non-null  float64
 10  total_cases_per_million                74505 non-null  float64
 11  new_cases_per_million                  74503 non-null  float64
 12  new_cases_smoothed_per_million         73507 non-null  float64
 13  total_deaths_per_million               65229 non-null  float64
 14  new_deaths_per_million                 65387 non-null  float64
 15  new_deaths_smoothed_per_million        73507 non-null  float64
 16  reproduction_rate                      61298 non-null  float64
 17  icu_patients                           7930 non-null   float64
 18  icu_patients_per_million               7930 non-null   float64
 19  hosp_patients                          9550 non-null   float64
 20  hosp_patients_per_million              9550 non-null   float64
 21  weekly_icu_admissions                  697 non-null    float64
 22  weekly_icu_admissions_per_million      697 non-null    float64
 23  weekly_hosp_admissions                 1224 non-null   float64
 24  weekly_hosp_admissions_per_million     1224 non-null   float64
 25  new_tests                              34582 non-null  float64
 26  total_tests                            34364 non-null  float64
 27  total_tests_per_thousand               34364 non-null  float64
 28  new_tests_per_thousand                 34582 non-null  float64
 29  new_tests_smoothed                     39573 non-null  float64
 30  new_tests_smoothed_per_thousand        39573 non-null  float64
 31  positive_rate                          38264 non-null  float64
 32  tests_per_case                         37653 non-null  float64
 33  tests_units                            40920 non-null  object 
 34  total_vaccinations                     4978 non-null   float64
 35  people_vaccinated                      4471 non-null   float64
 36  people_fully_vaccinated                2996 non-null   float64
 37  new_vaccinations                       4246 non-null   float64
 38  new_vaccinations_smoothed              7571 non-null   float64
 39  total_vaccinations_per_hundred         4978 non-null   float64
 40  people_vaccinated_per_hundred          4471 non-null   float64
 41  people_fully_vaccinated_per_hundred    2996 non-null   float64
 42  new_vaccinations_smoothed_per_million  7571 non-null   float64
 43  stringency_index                       65065 non-null  float64
 44  population                             75798 non-null  float64
 45  population_density                     71134 non-null  float64
 46  median_age                             69108 non-null  float64
 47  aged_65_older                          68314 non-null  float64
 48  aged_70_older                          68719 non-null  float64
 49  gdp_per_capita                         69348 non-null  float64
 50  extreme_poverty                        47317 non-null  float64
 51  cardiovasc_death_rate                  69965 non-null  float64
 52  diabetes_prevalence                    70872 non-null  float64
 53  female_smokers                         54974 non-null  float64
 54  male_smokers                           54166 non-null  float64
 55  handwashing_facilities                 35112 non-null  float64
 56  hospital_beds_per_thousand             64009 non-null  float64
 57  life_expectancy                        72418 non-null  float64
 58  human_development_index                69909 non-null  float64
dtypes: float64(54), object(5)
memory usage: 34.3+ MB


# ets first handle numerical features with nan value
Numerical_feat = [feature for feature in world_covid19_df.columns if world_covid19_df[feature].dtypes != 'O']
print('Total numerical features: ', len(Numerical_feat))
print('\nNumerical Features: ', Numerical_feat)

Total numerical features:  54

Numerical Features:  ['total_cases', 'new_cases', 'new_cases_smoothed', 'total_deaths', 'new_deaths', 'new_deaths_smoothed', 'total_cases_per_million', 'new_cases_per_million', 'new_cases_smoothed_per_million', 'total_deaths_per_million', 'new_deaths_per_million', 'new_deaths_smoothed_per_million', 'reproduction_rate', 'icu_patients', 'icu_patients_per_million', 'hosp_patients', 'hosp_patients_per_million', 'weekly_icu_admissions', 'weekly_icu_admissions_per_million', 'weekly_hosp_admissions', 'weekly_hosp_admissions_per_million', 'new_tests', 'total_tests', 'total_tests_per_thousand', 'new_tests_per_thousand', 'new_tests_smoothed', 'new_tests_smoothed_per_thousand', 'positive_rate', 'tests_per_case', 'total_vaccinations', 'people_vaccinated', 'people_fully_vaccinated', 'new_vaccinations', 'new_vaccinations_smoothed', 'total_vaccinations_per_hundred', 'people_vaccinated_per_hundred', 'people_fully_vaccinated_per_hundred', 'new_vaccinations_smoothed_per_million', 'stringency_index', 'population', 'population_density', 'median_age', 'aged_65_older', 'aged_70_older', 'gdp_per_capita', 'extreme_poverty', 'cardiovasc_death_rate', 'diabetes_prevalence', 'female_smokers', 'male_smokers', 'handwashing_facilities', 'hospital_beds_per_thousand', 'life_expectancy', 'human_development_index']


# categorical features
categorical_feat = [feature for feature in world_covid19_df.columns if world_covid19_df[feature].dtypes=='O']
print('Total categorical features: ', len(categorical_feat))
print('\n',categorical_feat)

Total categorical features:  5

 ['iso_code', 'continent', 'location', 'date', 'tests_units']


## Replacing the numerical Missing Values
for feature in Numerical_feat:
    ## We will replace by using median since there are outliers
        world_covid19_df[feature].fillna(0,inplace=True)
    
world_covid19_df[Numerical_feat].isnull().sum()

total_cases                              0
new_cases                                0
new_cases_smoothed                       0
total_deaths                             0
new_deaths                               0
new_deaths_smoothed                      0
total_cases_per_million                  0
new_cases_per_million                    0
new_cases_smoothed_per_million           0
total_deaths_per_million                 0
new_deaths_per_million                   0
new_deaths_smoothed_per_million          0
reproduction_rate                        0
icu_patients                             0
icu_patients_per_million                 0
hosp_patients                            0
hosp_patients_per_million                0
weekly_icu_admissions                    0
weekly_icu_admissions_per_million        0
weekly_hosp_admissions                   0
weekly_hosp_admissions_per_million       0
new_tests                                0
total_tests                              0
total_tests_per_thousand                 0
new_tests_per_thousand                   0
new_tests_smoothed                       0
new_tests_smoothed_per_thousand          0
positive_rate                            0
tests_per_case                           0
total_vaccinations                       0
people_vaccinated                        0
people_fully_vaccinated                  0
new_vaccinations                         0
new_vaccinations_smoothed                0
total_vaccinations_per_hundred           0
people_vaccinated_per_hundred            0
people_fully_vaccinated_per_hundred      0
new_vaccinations_smoothed_per_million    0
stringency_index                         0
population                               0
population_density                       0
median_age                               0
aged_65_older                            0
aged_70_older                            0
gdp_per_capita                           0
extreme_poverty                          0
cardiovasc_death_rate                    0
diabetes_prevalence                      0
female_smokers                           0
male_smokers                             0
handwashing_facilities                   0
hospital_beds_per_thousand               0
life_expectancy                          0
human_development_index                  0
dtype: int64


world_covid19_df


#Store the clean DataFrame in a CSV file
world_covid19_df.to_csv('covid19_df_master.csv',index=False)


covid_df=pd.read_csv('covid19_df_master.csv')
#covid_df.hist(figsize=(15,15));


covid_df.describe().style.background_gradient(cmap="CMRmap_r")


#covid_df['date'] = pd.to_datetime(covid_df.date)


#covid_df['year'] = pd.DatetimeIndex(covid_df.date).year
#covid_df['month'] = pd.DatetimeIndex(covid_df.date).month
#covid_df['day'] = pd.DatetimeIndex(covid_df.date).day
#covid_df['weekday'] = pd.DatetimeIndex(covid_df.date).weekday


covid_df.head(10)


sum(covid_df.duplicated())

0


covid_df.isnull().sum()

iso_code                                     0
continent                                 3742
location                                     0
date                                         0
total_cases                                  0
new_cases                                    0
new_cases_smoothed                           0
total_deaths                                 0
new_deaths                                   0
new_deaths_smoothed                          0
total_cases_per_million                      0
new_cases_per_million                        0
new_cases_smoothed_per_million               0
total_deaths_per_million                     0
new_deaths_per_million                       0
new_deaths_smoothed_per_million              0
reproduction_rate                            0
icu_patients                                 0
icu_patients_per_million                     0
hosp_patients                                0
hosp_patients_per_million                    0
weekly_icu_admissions                        0
weekly_icu_admissions_per_million            0
weekly_hosp_admissions                       0
weekly_hosp_admissions_per_million           0
new_tests                                    0
total_tests                                  0
total_tests_per_thousand                     0
new_tests_per_thousand                       0
new_tests_smoothed                           0
new_tests_smoothed_per_thousand              0
positive_rate                                0
tests_per_case                               0
tests_units                              35295
total_vaccinations                           0
people_vaccinated                            0
people_fully_vaccinated                      0
new_vaccinations                             0
new_vaccinations_smoothed                    0
total_vaccinations_per_hundred               0
people_vaccinated_per_hundred                0
people_fully_vaccinated_per_hundred          0
new_vaccinations_smoothed_per_million        0
stringency_index                             0
population                                   0
population_density                           0
median_age                                   0
aged_65_older                                0
aged_70_older                                0
gdp_per_capita                               0
extreme_poverty                              0
cardiovasc_death_rate                        0
diabetes_prevalence                          0
female_smokers                               0
male_smokers                                 0
handwashing_facilities                       0
hospital_beds_per_thousand                   0
life_expectancy                              0
human_development_index                      0
dtype: int64


covid_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 76215 entries, 0 to 76214
Data columns (total 59 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               76215 non-null  object 
 1   continent                              72473 non-null  object 
 2   location                               76215 non-null  object 
 3   date                                   76215 non-null  object 
 4   total_cases                            76215 non-null  float64
 5   new_cases                              76215 non-null  float64
 6   new_cases_smoothed                     76215 non-null  float64
 7   total_deaths                           76215 non-null  float64
 8   new_deaths                             76215 non-null  float64
 9   new_deaths_smoothed                    76215 non-null  float64
 10  total_cases_per_million                76215 non-null  float64
 11  new_cases_per_million                  76215 non-null  float64
 12  new_cases_smoothed_per_million         76215 non-null  float64
 13  total_deaths_per_million               76215 non-null  float64
 14  new_deaths_per_million                 76215 non-null  float64
 15  new_deaths_smoothed_per_million        76215 non-null  float64
 16  reproduction_rate                      76215 non-null  float64
 17  icu_patients                           76215 non-null  float64
 18  icu_patients_per_million               76215 non-null  float64
 19  hosp_patients                          76215 non-null  float64
 20  hosp_patients_per_million              76215 non-null  float64
 21  weekly_icu_admissions                  76215 non-null  float64
 22  weekly_icu_admissions_per_million      76215 non-null  float64
 23  weekly_hosp_admissions                 76215 non-null  float64
 24  weekly_hosp_admissions_per_million     76215 non-null  float64
 25  new_tests                              76215 non-null  float64
 26  total_tests                            76215 non-null  float64
 27  total_tests_per_thousand               76215 non-null  float64
 28  new_tests_per_thousand                 76215 non-null  float64
 29  new_tests_smoothed                     76215 non-null  float64
 30  new_tests_smoothed_per_thousand        76215 non-null  float64
 31  positive_rate                          76215 non-null  float64
 32  tests_per_case                         76215 non-null  float64
 33  tests_units                            40920 non-null  object 
 34  total_vaccinations                     76215 non-null  float64
 35  people_vaccinated                      76215 non-null  float64
 36  people_fully_vaccinated                76215 non-null  float64
 37  new_vaccinations                       76215 non-null  float64
 38  new_vaccinations_smoothed              76215 non-null  float64
 39  total_vaccinations_per_hundred         76215 non-null  float64
 40  people_vaccinated_per_hundred          76215 non-null  float64
 41  people_fully_vaccinated_per_hundred    76215 non-null  float64
 42  new_vaccinations_smoothed_per_million  76215 non-null  float64
 43  stringency_index                       76215 non-null  float64
 44  population                             76215 non-null  float64
 45  population_density                     76215 non-null  float64
 46  median_age                             76215 non-null  float64
 47  aged_65_older                          76215 non-null  float64
 48  aged_70_older                          76215 non-null  float64
 49  gdp_per_capita                         76215 non-null  float64
 50  extreme_poverty                        76215 non-null  float64
 51  cardiovasc_death_rate                  76215 non-null  float64
 52  diabetes_prevalence                    76215 non-null  float64
 53  female_smokers                         76215 non-null  float64
 54  male_smokers                           76215 non-null  float64
 55  handwashing_facilities                 76215 non-null  float64
 56  hospital_beds_per_thousand             76215 non-null  float64
 57  life_expectancy                        76215 non-null  float64
 58  human_development_index                76215 non-null  float64
dtypes: float64(54), object(5)
memory usage: 34.3+ MB


covid_df.describe().T.style.background_gradient(cmap="CMRmap_r")


data_popu=covid_df.groupby('continent').sum()


plt.figure(figsize = (20,18)) 
sns.set_style('ticks')
#sum countries population in Asia
plt.subplot(221)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Asia']).set_title('sum countries population in Asia')

#sum countries population in North America
plt.subplot(222)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'North America']).set_title('sum countries population in North America')

#sum countries population in South America
plt.subplot(223)
sns.barplot(y='location', x='population',data=covid_df[covid_df['continent'] == 'South America']).set_title('sum countries population in South America')

#sum countries population in Europe
plt.subplot(224)
sns.set_style('ticks')
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Europe']).set_title('sum countries population in Europe')
plt.subplots_adjust(left=0.1, 
                    bottom=0.1,  
                    right=0.9,  
                    top=0.9,  
                    wspace=0.4,  
                    hspace=0.2) 
plt.show();


#sum countries population in Africa
plt.figure(figsize = (20,18))
plt.subplot(221)
sns.set_style('ticks')
#sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Africa']).set_title('sum countries population in Africa')
#sum countries population in Oceania
plt.subplot(222)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Oceania']).set_title('sum countries population in Oceania')
plt.subplots_adjust(left=0.1, 
                    bottom=0.1,  
                    right=0.9,  
                    top=0.9,  
                    wspace=0.4,  
                    hspace=0.2) 
plt.show();


#top countries total population in asia
top_popu_asia=covid_df[covid_df['continent'] == 'Asia']
print("The top 10 countries total population in the continent of Asia is :\n",top_popu_asia.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of Asia is :
 continent  location   
Asia       China          1.439324e+09
           India          1.380004e+09
           Indonesia      2.735236e+08
           Pakistan       2.208923e+08
           Bangladesh     1.646894e+08
           Japan          1.264765e+08
           Philippines    1.095811e+08
           Vietnam        9.733858e+07
           Turkey         8.433907e+07
           Iran           8.399295e+07
Name: population, dtype: float64


#top countries total population in North America
top_popu_north_america=covid_df[covid_df['continent'] == 'North America']
print("The top 10 countries total population in the continent of North America is :\n",top_popu_north_america.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of North America is :
 continent      location          
North America  United States         331002647.0
               Mexico                128932753.0
               Canada                 37742157.0
               Guatemala              17915567.0
               Haiti                  11402533.0
               Cuba                   11326616.0
               Dominican Republic     10847904.0
               Honduras                9904608.0
               Nicaragua               6624554.0
               El Salvador             6486201.0
Name: population, dtype: float64


#top countries total population in South America
top_popu_south_america=covid_df[covid_df['continent'] == 'South America']
print("The top 10 countries total population in the continent of South America is :\n",top_popu_south_america.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of South America is :
 continent      location 
South America  Brazil       212559409.0
               Colombia      50882884.0
               Argentina     45195777.0
               Peru          32971846.0
               Venezuela     28435943.0
               Chile         19116209.0
               Ecuador       17643060.0
               Bolivia       11673029.0
               Paraguay       7132530.0
               Uruguay        3473727.0
Name: population, dtype: float64


#top countries total population in Europe
top_popu_europe=covid_df[covid_df['continent'] == 'Europe']
print("The top 10 countries total population in the continent of Europe is :\n",top_popu_europe.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of Europe is :
 continent  location      
Europe     Russia            145934460.0
           Germany            83783945.0
           France             68147687.0
           United Kingdom     67886004.0
           Italy              60461828.0
           Spain              46754783.0
           Ukraine            43733759.0
           Poland             37846605.0
           Romania            19237682.0
           Netherlands        17134873.0
Name: population, dtype: float64


##Show two or more countries total population numbers the min
data=covid_df[covid_df['continent'] == 'Europe']
data.groupby(['continent','location'])['population'].min().nsmallest(10)

continent  location      
Europe     Vatican              809.0
           Gibraltar          33691.0
           San Marino         33938.0
           Liechtenstein      38137.0
           Monaco             39244.0
           Faeroe Islands     48865.0
           Guernsey           67052.0
           Andorra            77265.0
           Isle of Man        85032.0
           Jersey            101073.0
Name: population, dtype: float64


#top countries total population in Europe
top_popu_africa=covid_df[covid_df['continent'] == 'Africa']
print(" The top 10 countries total population in the continent of Africa is :\n",top_popu_africa.groupby(['continent','location'])['population'].max().nlargest(10))

 The top 10 countries total population in the continent of Africa is :
 continent  location                    
Africa     Nigeria                         206139587.0
           Ethiopia                        114963583.0
           Egypt                           102334403.0
           Democratic Republic of Congo     89561404.0
           Tanzania                         59734213.0
           South Africa                     59308690.0
           Kenya                            53771300.0
           Uganda                           45741000.0
           Algeria                          43851043.0
           Sudan                            43849269.0
Name: population, dtype: float64


#top 10 countries total population in Oceania
top_popu_oceania=covid_df[covid_df['continent'] == 'Oceania']
print(" The top 10 countries total population in the continent of Oceania is :\n",top_popu_oceania.groupby(['continent','location'])['population'].max().nlargest(10))

 The top 10 countries total population in the continent of Oceania is :
 continent  location            
Oceania    Australia               25499881.0
           Papua New Guinea         8947027.0
           New Zealand              4822233.0
           Fiji                      896444.0
           Solomon Islands           686878.0
           Vanuatu                   307150.0
           Samoa                     198410.0
           Micronesia (country)      115021.0
           Marshall Islands           59194.0
Name: population, dtype: float64


continent_populations_df = covid_df.groupby(['continent'])['population'].sum()
continent_populations_df

continent
Africa           5.072744e+11
Asia             1.890449e+12
Europe           3.055237e+11
North America    2.476494e+11
Oceania          1.641354e+10
South America    1.701631e+11
Name: population, dtype: float64


#Show countries in  asia the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'Asia']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


#Show countries in  Europe the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'Europe']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


#Show countries in  Europe the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'North America']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


worldwide_spread=covid_df[["continent","location","total_cases","total_tests","date","total_deaths","positive_rate","total_vaccinations","people_fully_vaccinated"]]

df=worldwide_spread.dropna(axis=0)
df.sort_values("total_tests",ascending=False)
df_loc=df.groupby(['location']).max()
df_loc.drop(["date"],axis=1,inplace=True)
df_loc
for i,r in df_loc.iterrows():
    if r["total_tests"]>0:
        df_loc.loc[i,"test per confirmed(%)"]=(r["total_cases"]/r["total_tests"])*100
df_covid=df_loc.reset_index()  
df_covid.style.background_gradient(cmap="CMRmap_r")


fig = px.choropleth(covid_df, locations="location", 
                    color=np.log(covid_df["total_cases"]),
                    locationmode="country names", hover_name="location", 
                    animation_frame=covid_df["date"],
                    title='Cases over time', color_continuous_scale=px.colors.sequential.matter)
#fig.update(layout_coloraxis_showscale=False)
fig.show()


def plot_map(df, col, pal):
      
    fig = px.choropleth(df, locations="location", locationmode='country names', 
                  color=col, hover_name="location", 
                  title=col, hover_data=[col], color_continuous_scale=pal)
#    fig.update_layout(coloraxis_showscale=False)
    fig.show()


covid_deaths=covid_df[["continent","location","total_cases","date","total_deaths","total_deaths_per_million","total_cases_per_million","total_vaccinations"]]
df=covid_deaths.dropna(axis=0)
df_data=df.groupby(['location']).max()
df_data.drop(["date"],axis=1,inplace=True)
df_data.reset_index(inplace=True)

#df_data.drop(index=171,inplace=True)
df_data
df_data[df_data["continent"]=="Africa"].sum()

location                    AlgeriaAngolaBeninBotswanaBurkina FasoBurundiC...
continent                   AfricaAfricaAfricaAfricaAfricaAfricaAfricaAfri...
total_cases                                                       4.09742e+06
total_deaths                                                           109674
total_deaths_per_million                                              5353.83
total_cases_per_million                                                287182
total_vaccinations                                                8.19935e+06
dtype: object


plot_map(df_data,'total_cases', 'matter')


plot_map(df_data,'total_deaths', 'matter')


plot_map(df_data,'total_deaths_per_million', 'matter')


def plot_hbar(df, col, n, hover_data=[]):
    fig = px.bar(df.sort_values(col).tail(n), 
                 x=col, y="location", color='continent',  
                 text=col, orientation='h', width=700, hover_data=hover_data,
                 color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.update_layout(title=col, xaxis_title="", yaxis_title="", 
                      yaxis_categoryorder = 'total ascending',
                      uniformtext_minsize=8, uniformtext_mode='hide')
    fig.show()


plot_hbar(df_data, 'total_cases', 15)


plot_hbar(df_data, 'total_deaths', 15)


plot_hbar(df_data, 'total_deaths_per_million', 15)


plot_hbar(df_covid, "total_tests", 15)


plot_hbar(df_covid,"total_vaccinations", 15)


plot_hbar(df_covid,"people_fully_vaccinated", 15)


def plot_treemap(col):
    fig = px.treemap(df_data, path=["location"], values=col, height=700,
                 title=col, color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.data[0].textinfo = 'label+text+value'
    fig.show()
def plot_treemap_(col):
    fig = px.treemap(df_covid, path=["location"], values=col, height=700,
                 title=col, color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.data[0].textinfo = 'label+text+value'
    fig.show()


plot_treemap('total_cases')


plot_treemap('total_deaths')


plot_treemap_('total_tests')


plot_treemap_('test per confirmed(%)')


plot_treemap_('total_vaccinations')


plot_treemap_('people_fully_vaccinated')


covid_df['death_rate'] = (covid_df['new_deaths_smoothed_per_million'] / covid_df['new_cases_smoothed_per_million']).replace(np.inf,np.nan)
covid_df['population_coverage'] = covid_df['total_tests'] / covid_df['population']


trace1 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=covid_df.groupby(['date'])['new_deaths_smoothed_per_million'].mean(),
        xaxis='x2',
    yaxis='y2',
    name = "mean new deaths smoothed per million"
)
trace2 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=covid_df.groupby(['date'])['new_tests_smoothed_per_thousand'].mean(),
    name = "mean new tests smoothed per thousand"
)
trace3 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=(covid_df.groupby(['date'])['death_rate'].mean().replace([np.inf],np.nan).interpolate(method='linear', limit_direction='forward', axis=0) * 100).round(3),
    xaxis='x3',
    yaxis='y3',
    name = "interpolated death rate %"
)
trace4 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=((covid_df.groupby(['date'])['new_cases_per_million'].apply(lambda x: np.mean(x/1e+6))) * 100).round(6),
    xaxis='x4',
    yaxis='y4',
    name = "mean covid population d2d coverage %"
)

data = [trace1, trace2, trace3, trace4]
layout = go.Layout(
    xaxis=dict(
        domain=[0, 0.45]
    ),
    yaxis=dict(
        domain=[0, 0.45]
    ),
    xaxis2=dict(
        domain=[0.55, 1]
    ),
    xaxis3=dict(
        domain=[0, 0.45],
        anchor='y3'
    ),
    xaxis4=dict(
        domain=[0.55, 1],
        anchor='y4'
    ),
    yaxis2=dict(
        domain=[0, 0.45],
        anchor='x2'
    ),
    yaxis3=dict(
        domain=[0.55, 1]
    ),
    yaxis4=dict(
        domain=[0.55, 1],
        anchor='x4'
    ),
    title = 'Mean new deaths per 1M, new tests per 1K, death rate and covid mean coverage'
)
fig = go.Figure(data=data, layout=layout)
iplot(fig)


def plot_line(col,title):
    trace1 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Asia')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Asia')].groupby(['date','continent'])[col].sum(),
                    mode = "lines",
                    name = "Asia",
                    marker = dict(color = 'green'),
    )

    trace2 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Europe')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Europe')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "Europe",
                        marker = dict(color = 'red'),
    )

    trace3 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Africa')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Africa')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "Africa",
                        marker = dict(color = 'blue'),
                        #text= covid_df.university_name
    )

    trace4 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='North America')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='North America')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "North America",
                        marker = dict(color = 'black'),
    )

    trace5 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='South America')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='South America')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "South America",
                        marker = dict(color = 'brown'),
    )

    data = [trace1,trace2,trace3,trace4,trace5]
    layout = dict(title = title,
                  xaxis= dict(title= "#{} day by day".format(title),ticklen= 5,zeroline= False)
                 )
    fig = dict(data = data, layout = layout)
    iplot(fig)


plot_line('new_deaths_smoothed','New Deaths Smoothed')


plot_line('new_vaccinations_smoothed','new vaccinations smoothed')


plot_line('total_vaccinations','total_vaccinations')


plot_line('new_tests_smoothed','New tests smoothed')


plot_line('positive_rate','positive_rate')


def plot_line_mean(col,title):
    
    
    trace1 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Asia",
                        marker = dict(color = 'green'),
    )

    trace2 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Europe",
                        marker = dict(color = 'red'),
    )

    trace3 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Africa",
                        marker = dict(color = 'blue'),
    )

    trace4 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "North America",
                        marker = dict(color = 'black'),
    )

    trace5 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean(),
                        mode = "lines",
                        name = "South America",
                        marker = dict(color = 'brown'),
    )

    data = [trace1,trace2,trace3,trace4,trace5]
    layout = dict(title = title,
                  xaxis= dict(title= 'mean deaths/cases %',ticklen= 5,zeroline= False)
                 )
    fig = dict(data = data, layout = layout)
    iplot(fig)


plot_line_mean('death_rate','Mean death rate over continents')


plot_line_mean('population_coverage','Mean population test coverage over continents')


trace1 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['death_rate'].mean()*100,
                    mode = "lines",
                    name = "Asia",
                    marker = dict(color = 'green'),
)

trace2 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "Europe",
                    marker = dict(color = 'red'),
)

trace3 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "Africa",
                    marker = dict(color = 'blue'),
)

trace4 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "North America",
                    marker = dict(color = 'black'),
)

trace5 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean(),
                    mode = "lines",
                    name = "South America",
                    marker = dict(color = 'brown'),
)

data = [trace1,trace2,trace3,trace4,trace5]
layout = dict(title = 'Mean population test coverage over continents',
              xaxis= dict(title= 'mean tests/population %',ticklen= 5,zeroline= False)
             )
fig = dict(data = data, layout = layout)
iplot(fig)


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'new_deaths': np.sum, 'gdp_per_capita': np.mean, 'new_cases':np.sum}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['new_deaths'].isnull())&(~covid_df_grouped['new_cases'].isnull())&(~covid_df_grouped['gdp_per_capita'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths", y="gdp_per_capita", size="new_cases", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'handwashing_facilities': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'extreme_poverty':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['handwashing_facilities'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['extreme_poverty'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="handwashing_facilities", size="extreme_poverty", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'population_density': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'aged_70_older':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['population_density'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['aged_70_older'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="aged_70_older", size="population_density", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'life_expectancy': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'hospital_beds_per_thousand':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['life_expectancy'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['hospital_beds_per_thousand'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="life_expectancy", size="hospital_beds_per_thousand", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'death_rate': np.mean, 'stringency_index': np.mean, 'new_cases':np.sum}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['death_rate'].isnull())&(~covid_df_grouped['stringency_index'].isnull())&(~covid_df_grouped['new_cases'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="death_rate", y="stringency_index", size="new_cases", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_copy = world_covid19_df.copy()


covid_df_copy = covid_df.copy()


covid_df_copy.head(10)


correlations = covid_df_copy.corr()['total_cases'].abs().sort_values(ascending=False).drop('total_cases',axis=0).to_frame()
correlations.plot(kind='bar',figsize=(12,10));


# Function to see the correlation of each features

def corr(df):
    "argument df tp get the correlation for"
    return df.corr()


corr(covid_df_copy).style.background_gradient(cmap="CMRmap_r")


#owid_covid_data = pd.read_csv('https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv')
#owid_covid_data.head()


#Select Coloumn to clean
ColumnToClean = ['total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand']
#Replace the nan with emty string
covid_df_copy[['location']] = covid_df_copy[['location']].fillna('')
#Replace the Nan with 0
covid_df_copy[ColumnToClean] = covid_df_copy[ColumnToClean].fillna(0)
#Filter the data so we will get only overall world data
covid_df_copy = covid_df_copy.query('location=="World"' )
Data_For_Regression = pd.DataFrame(columns=['date','total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand'], data=covid_df_copy[['date','total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand']].values)
Data_For_Regression.head()


#set the index as date
Data_For_Regression['date'] = pd.to_datetime(Data_For_Regression['date'])
Data_For_Regression = Data_For_Regression.set_index('date')
Data_For_Regression.head()


#Plot the graph
Data_For_Regression['total_cases'].plot(figsize=(15,6), color="green")
plt.legend(loc=4)
plt.xlabel('Date')
plt.ylabel('Cases')
plt.show()

Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()

Data_For_Regression['new_cases'].plot(figsize=(15,6), color="blue")
plt.xlabel('Date')
plt.ylabel('New Cases')
plt.show()


# pick total death as forecast column
forecast_col = 'total_deaths'

# Chosing 30 days as number of forecast days
forecast_out = int(30)
print('length =',len(Data_For_Regression), "and forecast_out =", forecast_out)

length = 424 and forecast_out = 30


# Creating label by shifting 'total_deaths' according to 'forecast_out'
Data_For_Regression['temp'] = Data_For_Regression[forecast_col].shift(-forecast_out)
print(Data_For_Regression.head(2))
print('\n')
# verify rows with NAN in Label column 
print(Data_For_Regression.tail(2))

           total_cases new_cases total_deaths new_deaths aged_65_older  \
date                                                                     
2020-01-22         557         0           17          0         8.696   
2020-01-23         655        98           18          1         8.696   

           aged_70_older gdp_per_capita diabetes_prevalence female_smokers  \
date                                                                         
2020-01-22         5.355        15469.2                8.51          6.434   
2020-01-23         5.355        15469.2                8.51          6.434   

           male_smokers hospital_beds_per_thousand  temp  
date                                                      
2020-01-22       34.635                      2.705  2252  
2020-01-23       34.635                      2.705  2459  


            total_cases new_cases total_deaths new_deaths aged_65_older  \
date                                                                      
2021-03-19  1.22316e+08    526273  2.70144e+06      10410         8.696   
2021-03-20  1.22814e+08    498140  2.70964e+06       8194         8.696   

           aged_70_older gdp_per_capita diabetes_prevalence female_smokers  \
date                                                                         
2021-03-19         5.355        15469.2                8.51          6.434   
2021-03-20         5.355        15469.2                8.51          6.434   

           male_smokers hospital_beds_per_thousand temp  
date                                                     
2021-03-19       34.635                      2.705  NaN  
2021-03-20       34.635                      2.705  NaN


# Define features Matrix X by excluding the label column which we just created 
X = np.array(Data_For_Regression.drop(['temp'], 1))

# Using a feature in sklearn, preposessing to scale features
X = preprocessing.scale(X)
print(X[1,:])

[-0.96277535 -1.30745477 -1.17772698 -1.57016705  0.          0.
  0.          0.          0.          0.          0.        ]


# X contains last 'n= forecast_out' rows for which we don't have label data
# Put those rows in different Matrix X_forecast_out by X_forecast_out = X[end-forecast_out:end]

X_forecast_out = X[-forecast_out:]
X = X[:-forecast_out]
print ("Length of X_forecast_out:", len(X_forecast_out), "& Length of X :", len(X))

Length of X_forecast_out: 30 & Length of X : 394


# Define vector y for the data we have prediction for
# make sure length of X and y are identical
y = np.array(Data_For_Regression['temp'])
y = y[:-forecast_out]
print('Length of y: ',len(y))

Length of y:  394


# (split into test and train data)
# test_size = 0.2 ==> 20% data is test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
print('length of X_train and x_test: ', len(X_train), len(X_test))

length of X_train and x_test:  315 79


# Create linear regression object
lr = LinearRegression()

# Train the model using the training sets
lr.fit(X_train, y_train)
# Test
accuracy = lr.score(X_test, y_test)
print("Accuracy of Linear Regression: ", accuracy)

Accuracy of Linear Regression:  0.9977341359065376


# Predict using our Model
forecast_prediction = lr.predict(X_forecast_out)
print(forecast_prediction)

[2761369.60822026 2742437.89032144 2716729.72549334 2723886.09683447
 2788747.50374794 2821086.80735987 2819915.21601815 2830601.30857385
 2810759.52283328 2776173.46813663 2795955.78519842 2827930.95955923
 2878011.83052154 2883045.16751441 2893069.35882272 2877604.12019003
 2855573.53005105 2854086.52866266 2915178.08026103 2937093.14712452
 2950239.62234392 2962518.40862667 2956578.76082901 2916684.33256088
 2929072.89997022 2992631.12646166 3021011.48961908 3038624.40664073
 3041431.8177346  3028397.38128222]


Data_For_Regression.tail()


last_date = Data_For_Regression.iloc[-1].name 
last_date

Timestamp('2021-03-20 00:00:00')


todays_date = datetime.strptime(last_date.strftime("%Y-%m-%d"), "%Y-%m-%d")
todays_date = todays_date + timedelta(days=1)
todays_date = datetime.strptime(todays_date.strftime("%Y-%m-%d"), "%Y-%m-%d")
index = pd.date_range(todays_date, periods=30, freq='D')
columns = ['total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand','temp','forecast']
temp_df = pd.DataFrame(index=index, columns=columns)
temp_df


j=0
for i in forecast_prediction:
    temp_df.iat[j,12] = i
    j= j+1

temp_df


#Append the forcasted - Initially did it for easness but kater decided to use xgboost also
Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
temp_df['forecast'].plot(figsize=(15,6), color="orange")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()


#  XGboost algorithm to see if we can get better results
xgb_model = xgb.XGBRegressor(objective ='reg:squarederror',colsample_bytree=0.4,
                 gamma=0,                 
                 learning_rate=0.07,
                 max_depth=3,
                 min_child_weight=1.5,
                 n_estimators=10000,                                                                    
                 reg_alpha=0.75,
                 reg_lambda=0.45,
                 subsample=0.6) 

traindf, testdf = train_test_split(X_train, test_size = 0.2)

xgb_model.fit(X_train,y_train)

xgforecast_prediction = xgb_model.predict(X_forecast_out)

xgforecast_prediction

array([2704656.8, 2664913.5, 2536690.5, 2613490.5, 2718172.5, 2689632. ,
       2673268.8, 2692658.8, 2692065.8, 2523291.5, 2579734.8, 2612704.2,
       2710746.8, 2683083.2, 2674768.8, 2685463.5, 2556501.8, 2596244.8,
       2673547. , 2670320.2, 2676758.2, 2687230.2, 2673305.8, 2559467. ,
       2608374.2, 2668408.5, 2656320.8, 2672826.5, 2676134.5, 2675404.8],
      dtype=float32)


#Setting the temperory df with XGboost forecasted data
j=0
for i in xgforecast_prediction:
    temp_df.iat[j,12] = i
    j= j+1


Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
temp_df['forecast'].plot(figsize=(15,6), color="orange")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()


covid_df_copy = covid_df.copy()


covid_df_copy.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 76215 entries, 0 to 76214
Data columns (total 61 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               76215 non-null  object 
 1   continent                              72473 non-null  object 
 2   location                               76215 non-null  object 
 3   date                                   76215 non-null  object 
 4   total_cases                            76215 non-null  float64
 5   new_cases                              76215 non-null  float64
 6   new_cases_smoothed                     76215 non-null  float64
 7   total_deaths                           76215 non-null  float64
 8   new_deaths                             76215 non-null  float64
 9   new_deaths_smoothed                    76215 non-null  float64
 10  total_cases_per_million                76215 non-null  float64
 11  new_cases_per_million                  76215 non-null  float64
 12  new_cases_smoothed_per_million         76215 non-null  float64
 13  total_deaths_per_million               76215 non-null  float64
 14  new_deaths_per_million                 76215 non-null  float64
 15  new_deaths_smoothed_per_million        76215 non-null  float64
 16  reproduction_rate                      76215 non-null  float64
 17  icu_patients                           76215 non-null  float64
 18  icu_patients_per_million               76215 non-null  float64
 19  hosp_patients                          76215 non-null  float64
 20  hosp_patients_per_million              76215 non-null  float64
 21  weekly_icu_admissions                  76215 non-null  float64
 22  weekly_icu_admissions_per_million      76215 non-null  float64
 23  weekly_hosp_admissions                 76215 non-null  float64
 24  weekly_hosp_admissions_per_million     76215 non-null  float64
 25  new_tests                              76215 non-null  float64
 26  total_tests                            76215 non-null  float64
 27  total_tests_per_thousand               76215 non-null  float64
 28  new_tests_per_thousand                 76215 non-null  float64
 29  new_tests_smoothed                     76215 non-null  float64
 30  new_tests_smoothed_per_thousand        76215 non-null  float64
 31  positive_rate                          76215 non-null  float64
 32  tests_per_case                         76215 non-null  float64
 33  tests_units                            40920 non-null  object 
 34  total_vaccinations                     76215 non-null  float64
 35  people_vaccinated                      76215 non-null  float64
 36  people_fully_vaccinated                76215 non-null  float64
 37  new_vaccinations                       76215 non-null  float64
 38  new_vaccinations_smoothed              76215 non-null  float64
 39  total_vaccinations_per_hundred         76215 non-null  float64
 40  people_vaccinated_per_hundred          76215 non-null  float64
 41  people_fully_vaccinated_per_hundred    76215 non-null  float64
 42  new_vaccinations_smoothed_per_million  76215 non-null  float64
 43  stringency_index                       76215 non-null  float64
 44  population                             76215 non-null  float64
 45  population_density                     76215 non-null  float64
 46  median_age                             76215 non-null  float64
 47  aged_65_older                          76215 non-null  float64
 48  aged_70_older                          76215 non-null  float64
 49  gdp_per_capita                         76215 non-null  float64
 50  extreme_poverty                        76215 non-null  float64
 51  cardiovasc_death_rate                  76215 non-null  float64
 52  diabetes_prevalence                    76215 non-null  float64
 53  female_smokers                         76215 non-null  float64
 54  male_smokers                           76215 non-null  float64
 55  handwashing_facilities                 76215 non-null  float64
 56  hospital_beds_per_thousand             76215 non-null  float64
 57  life_expectancy                        76215 non-null  float64
 58  human_development_index                76215 non-null  float64
 59  death_rate                             68898 non-null  float64
 60  population_coverage                    75798 non-null  float64
dtypes: float64(56), object(5)
memory usage: 35.5+ MB


#it decided to Create a column the High Risk and base it off of total_deaths_per_million which is the Total deaths attributed to COVID-19 per 1,000,000 people
covid_df_copy['HighRisk'] = zscore(covid_df_copy['total_deaths_per_million']) > 0.65


covid_df_copy.head(20)


corr = covid_df_copy[['death_rate', 'total_deaths_per_million', 'aged_65_older','extreme_poverty', 'icu_patients', 'life_expectancy', 'cardiovasc_death_rate', 'diabetes_prevalence', 'human_development_index', 'population_density', 'aged_70_older', 'population_coverage']].corr()
corr.style.background_gradient(cmap='coolwarm')
#Total deaths attributed to COVID-19 per 1,000,000 people
#With the new data the correlations seem stronger on aged_70_older, 'cardiovasc_death_rate', 'diabetes_prevalence', 'human_development_index', 'population_density', 'aged_70_older',and  'population_coverage' than before.


predictors = ['diabetes_prevalence','icu_patients','life_expectancy', 'cardiovasc_death_rate', 'human_development_index', 'aged_70_older', 'population_density', 'female_smokers', 'male_smokers', 'extreme_poverty']
target = 'HighRisk'
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values

# Split the data into training and test sets, and scale
scaler = StandardScaler()

# unscaled version (note that scaling is only used on predictor variables)
X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)

# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)
print('First 10 Rows of Scaled Data: \n\n', X_train[0:10:,], '\n')

knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
predictions = knn.predict(X_test)
accuracy = (predictions == y_test).mean()
print('Accuracy:', round(accuracy * 100, 2), '%')

First 10 Rows of Scaled Data: 

 [[ 2.16970375e+00 -9.92836241e-02  4.45157032e-01 -6.32460446e-01
   7.48536558e-01 -8.31170980e-01  1.00417221e+00 -1.78831296e-01
   7.75762571e-01 -4.86384094e-01]
 [ 2.22119711e+00 -9.92836241e-02  3.80613143e-01  1.84617450e-01
   5.78461190e-01 -3.67873461e-01 -1.38292306e-01 -6.58327027e-01
   1.03379387e+00 -4.80475136e-01]
 [ 1.23814206e+00 -9.92836241e-02  1.24722329e-01  1.64963247e-01
   2.86903415e-01 -1.79343481e-01 -1.95825003e-01 -1.89993855e-02
   1.06067213e+00 -4.86384094e-01]
 [-1.46525932e+00 -9.92836241e-02 -4.41321860e-01 -3.05476685e-03
  -4.94633396e-01 -7.03878840e-01 -1.36518668e-01 -6.98285004e-01
  -5.84277375e-01  2.44445898e+00]
 [-7.49386104e-02 -9.92836241e-02  4.80570493e-01 -5.65009433e-01
   6.06807084e-01  1.22706265e+00 -1.85802333e-01  6.40307245e-01
  -1.75727826e-01 -4.80475136e-01]
 [ 5.44889451e+00 -9.92836241e-02  2.40101670e-01  2.40469736e+00
   1.49223355e-01 -1.14928665e+00 -1.47735658e-02 -7.58221971e-01
  -1.24548257e+00 -4.86384094e-01]
 [-4.04964233e-01 -9.92836241e-02 -3.06522235e-01 -2.68311729e-01
   1.69470423e-01 -4.49065205e-01 -1.69032883e-01  5.09270753e-02
   5.39233885e-01  6.30408932e-01]
 [-2.17715653e-01 -9.92836241e-02  1.27007069e-01  7.97293125e-01
   2.05915145e-01 -4.49065205e-01 -1.07569740e-01 -4.78516128e-01
   2.84538858e+00 -1.49573499e-01]
 [ 1.14217716e+00 -9.92836241e-02  4.68004426e-01 -4.85906499e-01
   6.18955325e-01  1.14800514e-02 -1.32914258e-01  6.50296739e-01
   9.63910390e-01 -4.74566179e-01]
 [-1.17422146e-02 -9.92836241e-02 -2.81390101e-01  8.06492010e-01
  -3.77200403e-01 -6.76126860e-01 -1.88501293e-01 -5.88400566e-01
   1.56598341e+00  1.69993030e+00]] 

Accuracy: 90.19 %


n = 8
accuracies = []
ks = np.arange(1, n+1, 2)
for k in ks:
    print(k, ' ', end='')
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)
    acc = (predictions == y_test).mean()
    accuracies.append(acc)
print('done')

def get_best(ks, accuracies):
    maximum = np.array(accuracies).max()
    indexMax = np.where(accuracies == maximum)
    return ks[indexMax], maximum

best_k, best_acc = get_best(ks, accuracies)
print('best k = {}, best accuracy: {:0.3f}%'.format(best_k, best_acc * 100))

1  3  5  7  done
best k = [7], best accuracy: 90.518%


print('Comparison of predictions to y_test values: \n\n', predictions == y_test)
print('\nPredictions:\n\n', predictions)
print('\nY_test values:\n\n', y_test)

Comparison of predictions to y_test values: 

 [ True  True  True ...  True  True  True]

Predictions:

 [ True False False ... False False False]

Y_test values:

 [ True False False ... False False False]


predictors = ['diabetes_prevalence','icu_patients','life_expectancy', 'cardiovasc_death_rate','human_development_index', 'aged_70_older', 'population_density', 'female_smokers', 'male_smokers', 'extreme_poverty']
target = 'HighRisk'
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values
# Split the data into training and test sets, and scale
scaler = StandardScaler()

# unscaled version (note that scaling is only used on predictor variables)
X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)

# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)

ks = np.arange(1, 8, 2)
for k in ks:
    best_acc = 0
    selected = []
    remaining = list(range(X_train.shape[1]))
    n = 11
    better = True
    while len(selected) < n and better == True:
        # find the single features that works best in conjunction
        # with the already selected features
        acc_max = 0
        for i in remaining:
            # make a version of the training data with just selected, feature i
            selectedFi = selected.copy()
            selectedFi.append(i)
            X_si = X_train[:,selectedFi]
            y_siTrain = y_train[~np.isnan(X_si).any(axis=1)]
            X_si=X_si[~np.isnan(X_si).any(axis=1)]
            knn = KNeighborsClassifier(n_neighbors=k)
            knn.fit(X_si, y_siTrain)
            X_testSi = X_test[:,selectedFi]
            y_siTest = y_test[~np.isnan(X_testSi).any(axis=1)]
            X_testSi = X_testSi[~np.isnan(X_testSi).any(axis=1)]
            predictions = knn.predict(X_testSi)

            acc = (predictions == y_siTest).mean()
            if (acc > acc_max):
                acc_max = acc
                i_min = i
                if (best_acc < acc):
                    best_acc = acc
                    better = True
                else:
                    better = False


        if (better == True):        
            remaining.remove(i_min)
            selected.append(i_min)
            print('k: {}; num features: {}; features: {}; bestAcc: {:.2f}%'.format(k, len(selected), [predictors[x] for x in selected], best_acc*100))

k: 1; num features: 1; features: ['icu_patients']; bestAcc: 86.57%
k: 1; num features: 2; features: ['icu_patients', 'male_smokers']; bestAcc: 87.74%
k: 1; num features: 3; features: ['icu_patients', 'male_smokers', 'extreme_poverty']; bestAcc: 88.32%
k: 1; num features: 4; features: ['icu_patients', 'male_smokers', 'extreme_poverty', 'life_expectancy']; bestAcc: 88.42%
k: 1; num features: 5; features: ['icu_patients', 'male_smokers', 'extreme_poverty', 'life_expectancy', 'aged_70_older']; bestAcc: 88.46%
k: 3; num features: 1; features: ['icu_patients']; bestAcc: 86.88%
k: 3; num features: 2; features: ['icu_patients', 'life_expectancy']; bestAcc: 89.28%
k: 3; num features: 3; features: ['icu_patients', 'life_expectancy', 'female_smokers']; bestAcc: 89.80%
k: 3; num features: 4; features: ['icu_patients', 'life_expectancy', 'female_smokers', 'human_development_index']; bestAcc: 89.83%
k: 3; num features: 5; features: ['icu_patients', 'life_expectancy', 'female_smokers', 'human_development_index', 'population_density']; bestAcc: 90.09%
k: 5; num features: 1; features: ['life_expectancy']; bestAcc: 87.97%
k: 5; num features: 2; features: ['life_expectancy', 'icu_patients']; bestAcc: 89.88%
k: 5; num features: 3; features: ['life_expectancy', 'icu_patients', 'female_smokers']; bestAcc: 90.33%
k: 7; num features: 1; features: ['population_density']; bestAcc: 88.38%
k: 7; num features: 2; features: ['population_density', 'icu_patients']; bestAcc: 89.67%
k: 7; num features: 3; features: ['population_density', 'icu_patients', 'female_smokers']; bestAcc: 90.22%
k: 7; num features: 4; features: ['population_density', 'icu_patients', 'female_smokers', 'human_development_index']; bestAcc: 90.53%


# change default plot size
rcParams['figure.figsize'] = 10,8
sns.scatterplot(data=covid_df_copy, x='male_smokers', y='cardiovasc_death_rate', hue='HighRisk', style='HighRisk');
plt.xlabel("Cardiovascular Death Rate")
plt.ylabel("Male Smokers");


sns.scatterplot(data=covid_df_copy, x='life_expectancy', y='diabetes_prevalence', hue='HighRisk', style='HighRisk')
plt.xlabel("Life Expectancy")
plt.ylabel("% of Obesity");


sns.scatterplot(data=covid_df_copy, x='human_development_index', y='positive_rate', hue='HighRisk', style='HighRisk');
plt.xlabel("Human Development Index")
plt.ylabel("positive_rate");


sns.scatterplot(data=covid_df_copy, x='aged_65_older', y='diabetes_prevalence', hue='HighRisk', style='HighRisk');
plt.xlabel("% Age 65 and older")
plt.ylabel("% of diabetes_prevalence");


k = 7
predictors = ['diabetes_prevalence','icu_patients','female_smokers','male_smokers', 'human_development_index', 'life_expectancy','cardiovasc_death_rate','positive_rate']
target = 'HighRisk'

# unscaled version (note that scaling is only used on predictor variables)
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values

# Split the data into training and test sets, and scale
scaler = StandardScaler()

X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)
# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)

#Remove data rows with nan
y_train = y_train[~np.isnan(X_train).any(axis=1)]
X_train = X_train[~np.isnan(X_train).any(axis=1)]

y_test = y_test[~np.isnan(X_test).any(axis=1)]
X_test = X_test[~np.isnan(X_test).any(axis=1)]

knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
predictions = knn.predict(X_test)

acc = (predictions == y_test).mean()

print('Comparison of predictions to y_test values: \n\n', predictions == y_test)
print('\nPredictions:\n\n', predictions)
print('\nY_test values:\n\n', y_test)

print('\nAccurancy: ', acc)

Comparison of predictions to y_test values: 

 [ True  True  True ...  True  True  True]

Predictions:

 [ True False False ... False False False]

Y_test values:

 [ True False False ... False False False]

Accurancy:  0.937109118740433

	source	description
column
iso_code	International Organization for Standardization	ISO 3166-1 alpha-3 – three-letter country codes
continent	Our World in Data	Continent of the geographical location
location	Our World in Data	Geographical location
date	Our World in Data	Date of observation
total_cases	COVID-19 Data Repository by the Center for Sys...	Total confirmed cases of COVID-19
new_cases	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19
new_cases_smoothed	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 (7-day smoothed)
total_deaths	COVID-19 Data Repository by the Center for Sys...	Total deaths attributed to COVID-19
new_deaths	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19
new_deaths_smoothed	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 (7-day smoot...
total_cases_per_million	COVID-19 Data Repository by the Center for Sys...	Total confirmed cases of COVID-19 per 1,000,00...
new_cases_per_million	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 per 1,000,000 ...
new_cases_smoothed_per_million	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 (7-day smoothe...
total_deaths_per_million	COVID-19 Data Repository by the Center for Sys...	Total deaths attributed to COVID-19 per 1,000,...
new_deaths_per_million	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 per 1,000,00...
new_deaths_smoothed_per_million	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 (7-day smoot...
reproduction_rate	Arroyo Marioli et al. (2020). https://doi.org/...	Real-time estimate of the effective reproducti...
icu_patients	European CDC for European countries / UK Gover...	Number of COVID-19 patients in intensive care ...
icu_patients_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients in intensive care ...
hosp_patients	European CDC for European countries / UK Gover...	Number of COVID-19 patients in hospital on a g...
hosp_patients_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients in hospital on a g...
weekly_icu_admissions	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_icu_admissions_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_hosp_admissions	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_hosp_admissions_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
total_tests	National government reports	Total tests for COVID-19
new_tests	National government reports	New tests for COVID-19 (only calculated for co...
total_tests_per_thousand	National government reports	Total tests for COVID-19 per 1,000 people
new_tests_per_thousand	National government reports	New tests for COVID-19 per 1,000 people
new_tests_smoothed	National government reports	New tests for COVID-19 (7-day smoothed). For c...
new_tests_smoothed_per_thousand	National government reports	New tests for COVID-19 (7-day smoothed) per 1,...
positive_rate	National government reports	The share of COVID-19 tests that are positive,...
tests_per_case	National government reports	Tests conducted per new confirmed case of COVI...
tests_units	National government reports	Units used by the location to report its testi...
total_vaccinations	National government reports	Total number of COVID-19 vaccination doses adm...
people_vaccinated	National government reports	Total number of people who received at least o...
people_fully_vaccinated	National government reports	Total number of people who received all doses ...
new_vaccinations	National government reports	New COVID-19 vaccination doses administered (o...
new_vaccinations_smoothed	National government reports	New COVID-19 vaccination doses administered (7...
total_vaccinations_per_hundred	National government reports	Total number of COVID-19 vaccination doses adm...
people_vaccinated_per_hundred	National government reports	Total number of people who received at least o...
people_fully_vaccinated_per_hundred	National government reports	Total number of people who received all doses ...
new_vaccinations_smoothed_per_million	National government reports	New COVID-19 vaccination doses administered (7...
stringency_index	Oxford COVID-19 Government Response Tracker, B...	Government Response Stringency Index: composit...
population	United Nations, Department of Economic and Soc...	Population in 2020
population_density	World Bank World Development Indicators, sourc...	Number of people divided by land area, measure...
median_age	UN Population Division, World Population Prosp...	Median age of the population, UN projection fo...
aged_65_older	World Bank World Development Indicators based ...	Share of the population that is 65 years and o...
aged_70_older	United Nations, Department of Economic and Soc...	Share of the population that is 70 years and o...
gdp_per_capita	World Bank World Development Indicators, sourc...	Gross domestic product at purchasing power par...
extreme_poverty	World Bank World Development Indicators, sourc...	Share of the population living in extreme pove...
cardiovasc_death_rate	Global Burden of Disease Collaborative Network...	Death rate from cardiovascular disease in 2017...
diabetes_prevalence	World Bank World Development Indicators, sourc...	Diabetes prevalence (% of population aged 20 t...
female_smokers	World Bank World Development Indicators, sourc...	Share of women who smoke, most recent year ava...
male_smokers	World Bank World Development Indicators, sourc...	Share of men who smoke, most recent year avail...
handwashing_facilities	United Nations Statistics Division	Share of the population with basic handwashing...
hospital_beds_per_thousand	OECD, Eurostat, World Bank, national governmen...	Hospital beds per 1,000 people, most recent ye...
life_expectancy	James C. Riley, Clio Infra, United Nations Pop...	Life expectancy at birth in 2019
human_development_index	United Nations Development Programme (UNDP)	A composite index measuring average achievemen...

	iso_code	continent	location	date	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	...	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index
0	AFG	Asia	Afghanistan	2020-02-24	1.0	1.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
1	AFG	Asia	Afghanistan	2020-02-25	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
2	AFG	Asia	Afghanistan	2020-02-26	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
3	AFG	Asia	Afghanistan	2020-02-27	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
4	AFG	Asia	Afghanistan	2020-02-28	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
76210	ZWE	Africa	Zimbabwe	2021-03-16	36535.0	31.0	30.571	1507.0	3.0	2.571	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
76211	ZWE	Africa	Zimbabwe	2021-03-17	36552.0	17.0	30.143	1508.0	1.0	2.714	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
76212	ZWE	Africa	Zimbabwe	2021-03-18	36611.0	59.0	33.429	1509.0	1.0	2.429	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
76213	ZWE	Africa	Zimbabwe	2021-03-19	36652.0	41.0	32.714	1510.0	1.0	2.000	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
76214	ZWE	Africa	Zimbabwe	2021-03-20	36662.0	10.0	27.286	1510.0	0.0	1.286	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571

	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	total_cases_per_million	new_cases_per_million	new_cases_smoothed_per_million	total_deaths_per_million	new_deaths_per_million	new_deaths_smoothed_per_million	reproduction_rate	icu_patients	icu_patients_per_million	hosp_patients	hosp_patients_per_million	weekly_icu_admissions	weekly_icu_admissions_per_million	weekly_hosp_admissions	weekly_hosp_admissions_per_million	new_tests	total_tests	total_tests_per_thousand	new_tests_per_thousand	new_tests_smoothed	new_tests_smoothed_per_thousand	positive_rate	tests_per_case	total_vaccinations	people_vaccinated	people_fully_vaccinated	new_vaccinations	new_vaccinations_smoothed	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	new_vaccinations_smoothed_per_million	stringency_index	population	population_density	median_age	aged_65_older	aged_70_older	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index
count	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000	76215.000000
mean	664429.456551	5129.566568	5063.112630	17076.098655	114.393531	113.178646	7873.626153	66.505456	65.390387	160.782550	1.209663	1.194381	0.817522	104.170898	2.427559	581.768497	19.617366	2.352516	0.175219	60.790989	1.757699	17638.245293	2187700.430243	80.015992	0.720085	19339.450148	0.782154	0.044136	80.619000	503611.229863	314467.331864	100983.102303	16332.660697	16596.512301	0.524075	0.339373	0.126228	243.715712	50.208742	129789029.585436	312.872929	27.700474	7.880594	5.023743	17411.789829	8.249080	236.141847	7.253194	7.601972	23.205725	23.489918	2.548185	69.505214	0.667534
std	4698196.905872	32191.869926	31633.387699	108136.089442	674.709265	652.256822	15662.046239	168.372816	141.179154	315.421600	3.623517	2.756024	0.509057	1038.799768	10.996649	4734.364944	85.827497	57.094248	3.765821	1554.711563	32.119539	102929.078224	15326886.721775	265.393666	3.099126	100759.298246	2.652978	0.082895	624.528191	7953373.735704	4766946.098613	1766444.270360	256803.603832	218893.084722	4.590345	2.888190	1.552936	1490.438593	29.046831	694541376.973729	1579.306203	12.419133	6.482936	4.370634	19609.485356	16.968226	133.738715	4.294111	10.021965	18.657876	33.329193	2.519296	17.534691	0.246698
min	0.000000	-74347.000000	-6223.000000	0.000000	-1918.000000	-232.143000	0.000000	-2153.437000	-276.825000	0.000000	-76.445000	-10.921000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	-239172.000000	0.000000	0.000000	-23.010000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	673.500000	1.000000	4.429000	10.000000	0.000000	0.000000	123.578000	0.061000	0.741000	1.603000	0.000000	0.000000	0.520000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	30.560000	2540916.000000	24.282000	19.600000	3.008000	1.783000	2896.913000	0.000000	140.448000	4.610000	0.000000	0.000000	0.000000	0.700000	66.470000	0.555000
50%	7821.000000	55.000000	63.000000	130.000000	1.000000	0.857000	1036.897000	5.861000	7.536000	19.611000	0.019000	0.099000	0.960000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	89.000000	0.007000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	55.560000	10099270.000000	80.080000	29.000000	5.440000	3.212000	10727.146000	0.500000	233.070000	6.930000	2.100000	24.500000	0.000000	2.000000	74.160000	0.737000
75%	87043.000000	662.000000	666.785500	1710.000000	11.000000	11.571000	7189.766500	55.940000	61.936000	139.170000	0.804000	0.975000	1.130000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3895.000000	378435.000000	30.874500	0.375000	5638.500000	0.534000	0.052000	18.200000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	73.150000	36910558.000000	204.430000	38.000000	13.260000	8.353000	25063.846000	4.500000	318.949000	9.750000	13.000000	37.700000	47.782000	3.600000	78.490000	0.828000
max	122813796.000000	880902.000000	739564.429000	2709639.000000	17895.000000	14424.000000	148592.506000	8652.658000	2648.773000	2327.774000	218.329000	63.140000	6.740000	30028.000000	189.561000	129812.000000	1042.535000	4037.019000	276.325000	116385.000000	2656.911000	2945871.000000	355058178.000000	3857.663000	327.086000	1858135.000000	59.929000	0.742000	44258.700000	436370147.000000	258958639.000000	99942889.000000	16650022.000000	11248913.000000	155.330000	89.160000	66.170000	54264.000000	100.000000	7794798729.000000	20546.766000	48.200000	27.049000	18.493000	116935.600000	77.600000	724.417000	30.530000	44.000000	78.100000	98.999000	13.800000	86.750000	0.957000

	count	mean	std	min	25%	50%	75%	max
total_cases	76215.000000	664429.456551	4698196.905872	0.000000	673.500000	7821.000000	87043.000000	122813796.000000
new_cases	76215.000000	5129.566568	32191.869926	-74347.000000	1.000000	55.000000	662.000000	880902.000000
new_cases_smoothed	76215.000000	5063.112630	31633.387699	-6223.000000	4.429000	63.000000	666.785500	739564.429000
total_deaths	76215.000000	17076.098655	108136.089442	0.000000	10.000000	130.000000	1710.000000	2709639.000000
new_deaths	76215.000000	114.393531	674.709265	-1918.000000	0.000000	1.000000	11.000000	17895.000000
new_deaths_smoothed	76215.000000	113.178646	652.256822	-232.143000	0.000000	0.857000	11.571000	14424.000000
total_cases_per_million	76215.000000	7873.626153	15662.046239	0.000000	123.578000	1036.897000	7189.766500	148592.506000
new_cases_per_million	76215.000000	66.505456	168.372816	-2153.437000	0.061000	5.861000	55.940000	8652.658000
new_cases_smoothed_per_million	76215.000000	65.390387	141.179154	-276.825000	0.741000	7.536000	61.936000	2648.773000
total_deaths_per_million	76215.000000	160.782550	315.421600	0.000000	1.603000	19.611000	139.170000	2327.774000
new_deaths_per_million	76215.000000	1.209663	3.623517	-76.445000	0.000000	0.019000	0.804000	218.329000
new_deaths_smoothed_per_million	76215.000000	1.194381	2.756024	-10.921000	0.000000	0.099000	0.975000	63.140000
reproduction_rate	76215.000000	0.817522	0.509057	0.000000	0.520000	0.960000	1.130000	6.740000
icu_patients	76215.000000	104.170898	1038.799768	0.000000	0.000000	0.000000	0.000000	30028.000000
icu_patients_per_million	76215.000000	2.427559	10.996649	0.000000	0.000000	0.000000	0.000000	189.561000
hosp_patients	76215.000000	581.768497	4734.364944	0.000000	0.000000	0.000000	0.000000	129812.000000
hosp_patients_per_million	76215.000000	19.617366	85.827497	0.000000	0.000000	0.000000	0.000000	1042.535000
weekly_icu_admissions	76215.000000	2.352516	57.094248	0.000000	0.000000	0.000000	0.000000	4037.019000
weekly_icu_admissions_per_million	76215.000000	0.175219	3.765821	0.000000	0.000000	0.000000	0.000000	276.325000
weekly_hosp_admissions	76215.000000	60.790989	1554.711563	0.000000	0.000000	0.000000	0.000000	116385.000000
weekly_hosp_admissions_per_million	76215.000000	1.757699	32.119539	0.000000	0.000000	0.000000	0.000000	2656.911000
new_tests	76215.000000	17638.245293	102929.078224	-239172.000000	0.000000	0.000000	3895.000000	2945871.000000
total_tests	76215.000000	2187700.430243	15326886.721775	0.000000	0.000000	0.000000	378435.000000	355058178.000000
total_tests_per_thousand	76215.000000	80.015992	265.393666	0.000000	0.000000	0.000000	30.874500	3857.663000
new_tests_per_thousand	76215.000000	0.720085	3.099126	-23.010000	0.000000	0.000000	0.375000	327.086000
new_tests_smoothed	76215.000000	19339.450148	100759.298246	0.000000	0.000000	89.000000	5638.500000	1858135.000000
new_tests_smoothed_per_thousand	76215.000000	0.782154	2.652978	0.000000	0.000000	0.007000	0.534000	59.929000
positive_rate	76215.000000	0.044136	0.082895	0.000000	0.000000	0.000000	0.052000	0.742000
tests_per_case	76215.000000	80.619000	624.528191	0.000000	0.000000	0.000000	18.200000	44258.700000
total_vaccinations	76215.000000	503611.229863	7953373.735704	0.000000	0.000000	0.000000	0.000000	436370147.000000
people_vaccinated	76215.000000	314467.331864	4766946.098613	0.000000	0.000000	0.000000	0.000000	258958639.000000
people_fully_vaccinated	76215.000000	100983.102303	1766444.270360	0.000000	0.000000	0.000000	0.000000	99942889.000000
new_vaccinations	76215.000000	16332.660697	256803.603832	0.000000	0.000000	0.000000	0.000000	16650022.000000
new_vaccinations_smoothed	76215.000000	16596.512301	218893.084722	0.000000	0.000000	0.000000	0.000000	11248913.000000
total_vaccinations_per_hundred	76215.000000	0.524075	4.590345	0.000000	0.000000	0.000000	0.000000	155.330000
people_vaccinated_per_hundred	76215.000000	0.339373	2.888190	0.000000	0.000000	0.000000	0.000000	89.160000
people_fully_vaccinated_per_hundred	76215.000000	0.126228	1.552936	0.000000	0.000000	0.000000	0.000000	66.170000
new_vaccinations_smoothed_per_million	76215.000000	243.715712	1490.438593	0.000000	0.000000	0.000000	0.000000	54264.000000
stringency_index	76215.000000	50.208742	29.046831	0.000000	30.560000	55.560000	73.150000	100.000000
population	76215.000000	129789029.585436	694541376.973729	0.000000	2540916.000000	10099270.000000	36910558.000000	7794798729.000000
population_density	76215.000000	312.872929	1579.306203	0.000000	24.282000	80.080000	204.430000	20546.766000
median_age	76215.000000	27.700474	12.419133	0.000000	19.600000	29.000000	38.000000	48.200000
aged_65_older	76215.000000	7.880594	6.482936	0.000000	3.008000	5.440000	13.260000	27.049000
aged_70_older	76215.000000	5.023743	4.370634	0.000000	1.783000	3.212000	8.353000	18.493000
gdp_per_capita	76215.000000	17411.789829	19609.485356	0.000000	2896.913000	10727.146000	25063.846000	116935.600000
extreme_poverty	76215.000000	8.249080	16.968226	0.000000	0.000000	0.500000	4.500000	77.600000
cardiovasc_death_rate	76215.000000	236.141847	133.738715	0.000000	140.448000	233.070000	318.949000	724.417000
diabetes_prevalence	76215.000000	7.253194	4.294111	0.000000	4.610000	6.930000	9.750000	30.530000
female_smokers	76215.000000	7.601972	10.021965	0.000000	0.000000	2.100000	13.000000	44.000000
male_smokers	76215.000000	23.205725	18.657876	0.000000	0.000000	24.500000	37.700000	78.100000
handwashing_facilities	76215.000000	23.489918	33.329193	0.000000	0.000000	0.000000	47.782000	98.999000
hospital_beds_per_thousand	76215.000000	2.548185	2.519296	0.000000	0.700000	2.000000	3.600000	13.800000
life_expectancy	76215.000000	69.505214	17.534691	0.000000	66.470000	74.160000	78.490000	86.750000
human_development_index	76215.000000	0.667534	0.246698	0.000000	0.555000	0.737000	0.828000	0.957000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
Asia	Afghanistan	32800.465473	56093.000000	1243.191816	2462.000000	0.000000	0.000000	159.079284	54000.000000
	Armenia	72477.093506	183127.000000	1282.075325	3332.000000	167847.475325	788953.000000	0.000000	0.000000
	Azerbaijan	81129.828571	245490.000000	1060.303896	3339.000000	0.000000	0.000000	8624.532468	453586.000000
	Bahrain	55488.445013	135326.000000	202.920716	498.000000	1134590.184143	3368947.000000	24745.964194	640104.000000
	Bangladesh	290780.796345	568706.000000	4216.869452	8668.000000	1760640.963446	4349615.000000	166798.676240	4760747.000000
	Bhutan	316.507895	869.000000	0.189474	1.000000	159224.386842	570591.000000	0.000000	0.000000
	Brunei	147.522546	205.000000	2.477454	3.000000	0.000000	0.000000	0.000000	0.000000
	Cambodia	276.434368	1578.000000	0.028640	2.000000	0.000000	0.000000	3161.455847	170659.000000
	China	85702.589623	101518.000000	4236.117925	4839.000000	589622.641509	160000000.000000	816007.075472	70000000.000000
	Georgia	76535.095116	277218.000000	885.956298	3691.000000	0.000000	0.000000	0.000000	0.000000
	Hong Kong	0.000000	0.000000	0.000000	0.000000	532269.370000	9918161.000000	30933.000000	330600.000000
	India	4672001.079327	11599130.000000	70708.079327	159755.000000	72672294.795673	231370546.000000	1949145.658654	44603841.000000
	Indonesia	392300.888021	1455788.000000	12082.231771	39447.000000	1865629.171875	7781193.000000	317826.398438	7835357.000000
	Iran	595969.260101	1793805.000000	27403.255051	61724.000000	2319587.229798	11844528.000000	32.828283	10000.000000
	Iraq	298074.859335	789390.000000	6821.565217	13969.000000	1884651.910486	7498360.000000	0.000000	0.000000
	Israel	239729.043038	827220.000000	1853.668354	6082.000000	4214791.891139	14437280.000000	1153293.881013	9686464.000000
	Japan	115264.412736	455212.000000	2036.846698	8802.000000	2125313.466981	8633325.000000	7521.330189	578835.000000
	Jordan	111707.718016	526666.000000	1381.872063	5788.000000	1220804.791123	5317747.000000	1947.830287	241868.000000
	Kazakhstan	120345.053619	281798.000000	1556.005362	3201.000000	3126088.214477	8211056.000000	627.857909	109995.000000
	Kuwait	89033.342711	217933.000000	544.427110	1215.000000	724549.557545	1941949.000000	1464.194373	360000.000000
	Kyrgyzstan	43689.866848	87389.000000	862.141304	1498.000000	0.000000	0.000000	0.000000	0.000000
	Laos	27.541436	49.000000	0.000000	0.000000	0.000000	0.000000	112.519337	40732.000000
	Lebanon	92094.444162	436575.000000	943.406091	5715.000000	0.000000	0.000000	4564.992386	135349.000000
	Macao	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	9632.441176	27637.000000
	Malaysia	59239.719715	331713.000000	282.427553	1229.000000	1793750.712589	7029970.000000	9899.733967	399525.000000
	Maldives	8346.089947	22373.000000	28.335979	65.000000	171012.134921	588650.000000	9865.481481	212711.000000
	Mongolia	749.364362	4806.000000	0.473404	4.000000	296730.375000	2061669.000000	3560.569149	204121.000000
	Myanmar	49369.986072	142212.000000	1093.337047	3204.000000	595327.573816	2482290.000000	1069.080780	380000.000000
	Nepal	101298.733967	275829.000000	735.420428	3016.000000	831554.337292	2218722.000000	5401.249406	1600000.000000
	Northern Cyprus	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1774.222222	11000.000000
	Oman	76451.038363	149135.000000	758.416880	1620.000000	0.000000	0.000000	4577.020460	109844.000000
	Pakistan	283551.843590	626802.000000	5985.046154	13843.000000	3156972.805128	9691087.000000	1289.430769	350000.000000
	Palestine	58333.060367	221391.000000	590.986877	2406.000000	0.000000	0.000000	0.000000	0.000000
	Philippines	232215.197115	656056.000000	4641.959135	12930.000000	3012351.947115	8938938.000000	1554.935096	240297.000000
	Qatar	100689.639896	173206.000000	158.971503	272.000000	698088.658031	1648555.000000	3645.077720	510000.000000
	Saudi Arabia	245337.190104	384653.000000	3584.747396	6602.000000	5915013.812500	14503622.000000	106634.174479	2999798.000000
	Singapore	40674.288416	60184.000000	21.498818	30.000000	373765.257683	8055714.000000	9986.940898	792423.000000
	South Korea	29387.498824	98665.000000	513.983529	1696.000000	2012652.098824	7176600.000000	21106.602353	676900.000000
	Sri Lanka	18167.811456	89655.000000	92.408115	544.000000	541971.038186	2309954.000000	48432.090692	824523.000000
	Syria	5446.060440	17240.000000	324.148352	1153.000000	0.000000	0.000000	0.000000	0.000000
	Taiwan	505.732558	1005.000000	6.051163	10.000000	85052.120930	183386.000000	0.000000	0.000000
	Tajikistan	9405.175385	13308.000000	71.316923	90.000000	0.000000	0.000000	0.000000	0.000000
	Thailand	5812.058824	27594.000000	49.151584	90.000000	864887.124434	2894666.000000	215.031674	53842.000000
	Timor	40.447802	271.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
	Turkey	835822.845333	2992694.000000	11075.733333	29959.000000	12276750.498667	35787480.000000	982927.338667	13029754.000000
	United Arab Emirates	115633.733813	438638.000000	428.280576	1433.000000	10221291.400480	34913667.000000	768939.309353	7181056.000000
	Uzbekistan	42940.285714	81339.000000	335.913747	622.000000	0.000000	0.000000	0.000000	0.000000
	Vietnam	897.810875	2572.000000	18.139480	35.000000	92152.125296	1469955.000000	353.342790	30971.000000
	Yemen	1629.878261	3278.000000	460.168116	737.000000	0.000000	0.000000	0.000000	0.000000

	date	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand
0	2020-01-22	557	0	17	0	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
1	2020-01-23	655	98	18	1	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
2	2020-01-24	941	286	26	8	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
3	2020-01-25	1433	492	42	16	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
4	2020-01-26	2118	685	56	14	8.696	5.355	15469.2	8.51	6.434	34.635	2.705

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp
date
2021-03-16	1.20697e+08	472966	2.67045e+06	9997	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-17	1.21236e+08	538804	2.68052e+06	10063	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-18	1.21789e+08	553312	2.69104e+06	10519	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-19	1.22316e+08	526273	2.70144e+06	10410	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-20	1.22814e+08	498140	2.70964e+06	8194	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp	forecast
2021-03-21	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-23	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-24	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-25	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-26	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-27	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-28	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-29	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-30	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-31	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-04	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-05	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-06	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-07	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-10	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-11	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-12	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-13	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-14	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-16	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-17	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-18	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-19	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp	forecast
2021-03-21	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.76137e+06
2021-03-22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.74244e+06
2021-03-23	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.71673e+06
2021-03-24	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.72389e+06
2021-03-25	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.78875e+06
2021-03-26	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.82109e+06
2021-03-27	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.81992e+06
2021-03-28	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.8306e+06
2021-03-29	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.81076e+06
2021-03-30	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.77617e+06
2021-03-31	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.79596e+06
2021-04-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.82793e+06
2021-04-02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.87801e+06
2021-04-03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.88305e+06
2021-04-04	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.89307e+06
2021-04-05	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.8776e+06
2021-04-06	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.85557e+06
2021-04-07	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.85409e+06
2021-04-08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.91518e+06
2021-04-09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.93709e+06
2021-04-10	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.95024e+06
2021-04-11	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.96252e+06
2021-04-12	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.95658e+06
2021-04-13	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.91668e+06
2021-04-14	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.92907e+06
2021-04-15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.99263e+06
2021-04-16	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.02101e+06
2021-04-17	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.03862e+06
2021-04-18	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.04143e+06
2021-04-19	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.0284e+06

	death_rate	total_deaths_per_million	aged_65_older	extreme_poverty	icu_patients	life_expectancy	cardiovasc_death_rate	diabetes_prevalence	human_development_index	population_density	aged_70_older	population_coverage
death_rate	1.000000	0.011712	0.019838	-0.004740	0.002655	0.001072	0.007339	-0.016454	-0.005875	0.000378	0.022357	-0.027813
total_deaths_per_million	0.011712	1.000000	0.261580	-0.190581	0.209748	0.087003	-0.210793	-0.044598	0.131226	-0.024086	0.264115	0.284074
aged_65_older	0.019838	0.261580	1.000000	-0.314490	0.152195	0.495638	-0.061668	0.077630	0.690167	-0.038343	0.965808	0.233574
extreme_poverty	-0.004740	-0.190581	-0.314490	1.000000	-0.042952	-0.145519	0.191294	-0.273647	-0.253455	-0.055936	-0.315749	-0.129305
icu_patients	0.002655	0.209748	0.152195	-0.042952	1.000000	0.062059	-0.068656	0.025804	0.101677	-0.012730	0.154094	0.124600
life_expectancy	0.001072	0.087003	0.495638	-0.145519	0.062059	1.000000	0.170786	0.436338	0.751472	0.123856	0.485926	0.167732
cardiovasc_death_rate	0.007339	-0.210793	-0.061668	0.191294	-0.068656	0.170786	1.000000	0.244890	0.152652	-0.179121	-0.098685	-0.098590
diabetes_prevalence	-0.016454	-0.044598	0.077630	-0.273647	0.025804	0.436338	0.244890	1.000000	0.461805	0.026118	0.018650	0.075327
human_development_index	-0.005875	0.131226	0.690167	-0.253455	0.101677	0.751472	0.152652	0.461805	1.000000	-0.128936	0.638597	0.249810
population_density	0.000378	-0.024086	-0.038343	-0.055936	-0.012730	0.123856	-0.179121	0.026118	-0.128936	1.000000	-0.047520	0.002514
aged_70_older	0.022357	0.264115	0.965808	-0.315749	0.154094	0.485926	-0.098685	0.018650	0.638597	-0.047520	1.000000	0.225655
population_coverage	-0.027813	0.284074	0.233574	-0.129305	0.124600	0.167732	-0.098590	0.075327	0.249810	0.002514	0.225655	1.000000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
Europe	Albania	27496.753846	120541.000000	542.628205	2133.000000	121225.482051	497742.000000	358.548718	33369.000000
	Andorra	3850.583333	11481.000000	61.265625	113.000000	4918.734375	162071.000000	52.361979	4914.000000
	Austria	143926.628205	511440.000000	2512.548718	9052.000000	3093094.464103	19277527.000000	88327.330769	1239208.000000
	Belarus	105512.888889	309293.000000	812.855297	2148.000000	526215.829457	5178695.000000	131.638243	30000.000000
	Belgium	271334.396594	827941.000000	11233.172749	22650.000000	3408751.282238	10322890.000000	100065.007299	1323086.000000
	Bosnia and Herzegovina	47326.703412	151337.000000	1662.503937	5773.000000	213201.230971	733032.000000	0.000000	0.000000
	Bulgaria	78287.687831	302480.000000	2912.796296	11966.000000	529062.817460	1915561.000000	25370.275132	366547.000000
	Croatia	73024.387179	256805.000000	1434.812821	5753.000000	388907.628205	1461537.000000	8242.951282	365082.000000
	Cyprus	9437.673740	41882.000000	63.230769	242.000000	602203.002653	3044737.000000	1503.787798	129438.000000
	Czechia	323394.974293	1459406.000000	5140.961440	24530.000000	0.000000	0.000000	95911.832905	1330675.000000
	Denmark	62748.303483	225540.000000	851.870647	2400.000000	4858681.820896	19408441.000000	79063.845771	935185.000000
	Estonia	14311.394872	94028.000000	150.310256	780.000000	323216.153846	1071562.000000	12716.071795	220882.000000
	Faeroe Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2280.510204	9342.000000
	Finland	17232.170264	71123.000000	344.328537	805.000000	1115747.035971	3734426.000000	48220.817746	812039.000000
	France	1138253.457346	4277183.000000	36869.215640	92119.000000	0.000000	0.000000	479563.850711	7927771.000000
	Germany	707616.916468	2669233.000000	18247.847255	74706.000000	2368382.556086	47511887.000000	769901.868735	10473852.000000
	Gibraltar	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	24921.085714	52331.000000
	Greece	55152.391858	235611.000000	1747.959288	7421.000000	1564811.786260	5944445.000000	97515.226463	1436491.000000
	Guernsey	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2345.041667	29383.000000
	Hungary	123337.568063	560971.000000	3960.986911	18068.000000	1059831.206806	3751450.000000	127689.473822	2038133.000000
	Iceland	3295.149100	6097.000000	15.313625	29.000000	132377.637532	290437.000000	2127.336761	52604.000000
	Ireland	66086.012821	229831.000000	1903.846154	4585.000000	1286446.820513	3786972.000000	44057.589744	639586.000000
	Isle of Man	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	15432.666667	33336.000000
	Italy	875866.281928	3356331.000000	42791.809639	104642.000000	13117156.293976	45894515.000000	586145.142169	7708889.000000
	Jersey	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5268.440000	45758.000000
	Kosovo	23996.236559	80295.000000	642.766129	1752.000000	0.000000	0.000000	0.000000	0.000000
	Latvia	18431.976923	97149.000000	324.702564	1821.000000	453499.400000	1671987.000000	7445.574359	102320.000000
	Liechtenstein	788.968586	2627.000000	13.811518	56.000000	0.000000	0.000000	66.479058	4215.000000
	Lithuania	50231.503876	208650.000000	739.069767	3464.000000	841210.359173	2264247.000000	31723.829457	399863.000000
	Luxembourg	19337.785166	58955.000000	232.685422	714.000000	815707.519182	2280826.000000	3365.920716	70339.000000
	Malta	6024.591687	27904.000000	83.332518	369.000000	256224.574572	772206.000000	9488.924205	140331.000000
	Moldova	68266.780423	214203.000000	1542.140212	4531.000000	0.000000	0.000000	268.455026	18593.000000
	Monaco	507.873057	2173.000000	5.569948	27.000000	0.000000	0.000000	93.505181	18081.000000
	Montenegro	22491.146341	86782.000000	313.325203	1194.000000	0.000000	0.000000	140.181572	7298.000000
	Netherlands	337849.726343	1211447.000000	7574.644501	16395.000000	365637.345269	7184008.000000	19897.066496	1887726.000000
	North Macedonia	34666.272494	118736.000000	1097.457584	3448.000000	199062.809769	578312.000000	13.624679	5300.000000
	Norway	24624.683673	86362.000000	300.262755	648.000000	1371938.622449	4274069.000000	57095.441327	758514.000000
	Poland	511944.769634	2036700.000000	11805.534031	49159.000000	3690909.712042	10639405.000000	341900.761780	4983494.000000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
North America	Anguilla	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	417.727273	5348.000000
	Antigua and Barbuda	159.664879	1033.000000	4.772118	28.000000	0.000000	0.000000	133.621984	25677.000000
	Bahamas	3864.724324	8800.000000	85.605405	186.000000	0.000000	0.000000	0.297297	110.000000
	Barbados	562.886179	3533.000000	9.544715	39.000000	0.000000	0.000000	3205.623306	58214.000000
	Belize	4180.584022	12400.000000	96.738292	316.000000	0.000000	0.000000	220.085399	15006.000000
	Bermuda	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2816.246154	30481.000000
	Canada	265005.852381	935932.000000	9559.716667	22635.000000	2676569.345238	26250445.000000	261255.052381	3862685.000000
	Cayman Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	4332.476190	39145.000000
	Costa Rica	78812.997368	211903.000000	1007.471053	2896.000000	209663.102632	623493.000000	3394.173684	248082.000000
	Cuba	10733.294118	65962.000000	124.740642	392.000000	774317.021390	2730305.000000	0.000000	0.000000
	Dominica	52.634615	156.000000	0.000000	0.000000	0.000000	0.000000	57.052198	13565.000000
	Dominican Republic	99771.244156	248989.000000	1566.116883	3269.000000	427707.618182	1263135.000000	10422.646753	675000.000000
	El Salvador	26734.095368	62531.000000	780.168937	1975.000000	162169.149864	717882.000000	339.269755	41512.000000
	Greenland	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	226.882353	5130.000000
	Grenada	54.082418	154.000000	0.211538	1.000000	0.000000	0.000000	32.285714	8606.000000
	Guatemala	73889.419598	187659.000000	2637.716080	6685.000000	309333.449749	995537.000000	980.753769	66399.000000
	Haiti	7147.516393	12700.000000	163.997268	251.000000	0.000000	0.000000	0.000000	0.000000
	Honduras	70863.101333	181931.000000	1897.346667	4430.000000	0.000000	0.000000	201.789333	37317.000000
	Jamaica	7204.192000	34665.000000	143.296000	524.000000	48877.738667	243363.000000	75.186667	16096.000000
	Mexico	670242.629213	2193639.000000	63141.078652	197827.000000	1581521.896629	5399163.000000	264364.887640	5459014.000000
	Montserrat	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	51.096774	932.000000
	Nicaragua	3943.362398	6582.000000	113.700272	176.000000	0.000000	0.000000	0.000000	0.000000
	Panama	127367.350133	350665.000000	2316.992042	6042.000000	627499.267905	2035210.000000	12984.485411	297165.000000
	Saint Kitts and Nevis	22.116343	44.000000	0.000000	0.000000	0.000000	0.000000	40.119114	7580.000000
	Saint Lucia	501.247312	4113.000000	5.475806	55.000000	0.000000	0.000000	106.801075	20247.000000
	Saint Vincent and the Grenadines	269.379032	1696.000000	0.919355	9.000000	0.000000	0.000000	49.287634	9383.000000
	Trinidad and Tobago	3476.973118	7839.000000	63.903226	140.000000	30720.443548	103786.000000	3.846774	991.000000
	Turks and Caicos Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	214.433333	6433.000000
	United States	9004664.099057	29785285.000000	197045.080189	541926.000000	113629930.792453	355058178.000000	8889080.884434	121441497.000000

	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	total_cases_per_million	new_cases_per_million	new_cases_smoothed_per_million	total_deaths_per_million	new_deaths_per_million	new_deaths_smoothed_per_million	reproduction_rate	icu_patients	icu_patients_per_million	hosp_patients	hosp_patients_per_million	weekly_icu_admissions	weekly_icu_admissions_per_million	weekly_hosp_admissions	weekly_hosp_admissions_per_million	new_tests	total_tests	total_tests_per_thousand	new_tests_per_thousand	new_tests_smoothed	new_tests_smoothed_per_thousand	positive_rate	tests_per_case	total_vaccinations	people_vaccinated	people_fully_vaccinated	new_vaccinations	new_vaccinations_smoothed	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	new_vaccinations_smoothed_per_million	stringency_index	population	population_density	median_age	aged_65_older	aged_70_older	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index	death_rate	population_coverage
total_cases	1.000000	0.874162	0.888154	0.983313	0.848058	0.876899	0.140310	0.067746	0.082189	0.169975	0.071839	0.095372	-0.053677	0.167050	0.044366	0.155312	0.019911	0.003233	-0.001386	0.060245	0.007456	0.176094	0.210690	0.008818	-0.002867	0.184394	-0.003935	-0.031146	-0.016797	0.709946	0.716938	0.637546	0.699287	0.766562	0.061655	0.069220	0.045063	0.048157	-0.143389	0.603536	-0.022085	-0.076957	-0.028515	-0.028776	-0.023861	-0.030544	-0.103823	-0.060493	-0.016033	-0.028103	0.003269	-0.042292	-0.181257	-0.101104	-0.006046	0.008587
new_cases	0.874162	1.000000	0.988770	0.894524	0.926816	0.923409	0.113827	0.112570	0.120201	0.146790	0.095649	0.114138	-0.051484	0.207915	0.064766	0.198959	0.036703	0.003244	-0.002144	0.064484	0.008696	0.197580	0.172913	0.000945	-0.001406	0.200244	-0.003066	-0.021606	-0.019654	0.388810	0.397605	0.328983	0.422973	0.454275	0.025148	0.029821	0.015983	0.018978	-0.158905	0.661523	-0.025341	-0.086924	-0.028955	-0.029078	-0.025403	-0.036756	-0.119975	-0.072198	-0.014383	-0.031940	-0.000706	-0.045197	-0.207708	-0.115344	-0.007221	0.000681
new_cases_smoothed	0.888154	0.988770	1.000000	0.906475	0.918715	0.939357	0.117262	0.102323	0.122074	0.149869	0.092143	0.118265	-0.053868	0.212243	0.065476	0.202595	0.036813	0.007140	0.000651	0.078322	0.013282	0.197794	0.178206	0.001922	-0.001699	0.204380	-0.002600	-0.021468	-0.019736	0.392009	0.401355	0.328814	0.425698	0.463595	0.026080	0.030955	0.016457	0.020343	-0.159214	0.664703	-0.025452	-0.087217	-0.029013	-0.029132	-0.025329	-0.036887	-0.120503	-0.072394	-0.014427	-0.032033	-0.000643	-0.045448	-0.208477	-0.115709	-0.007022	0.001657
total_deaths	0.983313	0.894524	0.906475	1.000000	0.881153	0.910655	0.132417	0.064787	0.078132	0.187885	0.077617	0.103195	-0.059426	0.141831	0.037020	0.134571	0.017193	0.002716	-0.003176	0.050593	0.005673	0.145829	0.163375	-0.002184	-0.008226	0.152508	-0.010534	-0.026620	-0.018823	0.665703	0.677479	0.602474	0.653199	0.716121	0.053589	0.062107	0.038132	0.039971	-0.160678	0.640373	-0.025668	-0.087175	-0.030545	-0.029817	-0.028874	-0.037296	-0.123561	-0.072404	-0.017543	-0.035624	0.004469	-0.049499	-0.205350	-0.114825	-0.001535	-0.002447
new_deaths	0.848058	0.926816	0.918715	0.881153	1.000000	0.971499	0.106557	0.085865	0.096648	0.153542	0.140592	0.147183	-0.058144	0.153560	0.054363	0.150057	0.033229	0.000592	-0.003276	0.028982	0.002989	0.143001	0.127968	-0.009556	-0.008984	0.140609	-0.013168	-0.011568	-0.021013	0.414428	0.429076	0.352333	0.456267	0.487689	0.027582	0.034202	0.017284	0.020900	-0.166023	0.679298	-0.027743	-0.093805	-0.032032	-0.031190	-0.031716	-0.040879	-0.131013	-0.078984	-0.016850	-0.035987	0.003875	-0.049041	-0.222544	-0.124281	0.008762	-0.009840
new_deaths_smoothed	0.876899	0.923409	0.939357	0.910655	0.971499	1.000000	0.111334	0.079456	0.097269	0.160171	0.115682	0.151781	-0.061976	0.156295	0.054274	0.152396	0.032897	0.006190	-0.001283	0.056241	0.009894	0.139525	0.134119	-0.008888	-0.010318	0.145490	-0.013247	-0.012398	-0.021468	0.434847	0.450076	0.370088	0.467670	0.511886	0.029955	0.036991	0.018918	0.023029	-0.169794	0.695507	-0.028383	-0.095988	-0.032732	-0.031858	-0.032321	-0.041816	-0.134150	-0.080795	-0.017246	-0.036835	0.004048	-0.050265	-0.227720	-0.127139	0.009072	-0.009179
total_cases_per_million	0.140310	0.113827	0.117262	0.132417	0.106557	0.111334	1.000000	0.588534	0.706893	0.830203	0.437590	0.580378	0.113436	0.189610	0.379739	0.222291	0.379806	0.082057	0.112887	0.074514	0.094312	0.184743	0.195524	0.457347	0.306539	0.201747	0.387508	0.200742	-0.042170	0.103211	0.123252	0.120889	0.094056	0.107851	0.250308	0.261211	0.199877	0.238136	0.047408	-0.032864	0.027198	0.128905	0.191239	0.182706	0.263809	-0.194549	-0.162586	0.042081	0.290454	0.090835	-0.119412	0.137358	0.125502	0.163102	-0.026569	0.456945
new_cases_per_million	0.067746	0.112570	0.102323	0.064787	0.085865	0.079456	0.588534	1.000000	0.845264	0.479247	0.525415	0.573209	0.161570	0.162670	0.380001	0.204918	0.422492	0.050180	0.074757	0.053348	0.077163	0.137356	0.105801	0.279451	0.248827	0.145248	0.293487	0.274428	-0.044086	0.022902	0.030287	0.026165	0.025943	0.028801	0.128378	0.135856	0.093364	0.139727	0.060453	-0.029948	0.027421	0.130760	0.201507	0.191215	0.186934	-0.156516	-0.110503	0.022212	0.277451	0.088948	-0.110486	0.145796	0.104595	0.141638	-0.031092	0.278986
new_cases_smoothed_per_million	0.082189	0.120201	0.122074	0.078132	0.096648	0.097269	0.706893	0.845264	1.000000	0.573430	0.548876	0.696430	0.172021	0.192666	0.453811	0.241222	0.503844	0.100595	0.144452	0.083918	0.134118	0.160067	0.128573	0.335165	0.282043	0.174152	0.348233	0.324376	-0.051688	0.028140	0.037136	0.031701	0.030964	0.036003	0.152240	0.158618	0.112353	0.166602	0.076521	-0.034918	0.032288	0.152835	0.235662	0.223876	0.219669	-0.183398	-0.130390	0.026003	0.324493	0.104041	-0.129319	0.169874	0.122631	0.166580	-0.035884	0.334678
total_deaths_per_million	0.169975	0.146790	0.149869	0.187885	0.153542	0.160171	0.830203	0.479247	0.573430	1.000000	0.470466	0.627766	0.113382	0.209748	0.394161	0.268544	0.407010	0.073335	0.081277	0.081456	0.089775	0.206481	0.196909	0.284645	0.213855	0.227330	0.266208	0.246467	-0.049904	0.109736	0.134283	0.124896	0.101472	0.115260	0.164580	0.193320	0.123952	0.155402	0.067364	-0.017309	-0.024086	0.137055	0.261580	0.264115	0.200522	-0.190581	-0.210793	-0.044598	0.319525	0.030308	-0.101904	0.143193	0.087003	0.131226	0.011712	0.284074
new_deaths_per_million	0.071839	0.095649	0.092143	0.077617	0.140592	0.115682	0.437590	0.525415	0.548876	0.470466	1.000000	0.761659	0.095104	0.147454	0.384704	0.201959	0.455957	0.042898	0.068872	0.034135	0.075834	0.113285	0.086355	0.169078	0.171336	0.116431	0.197733	0.278953	-0.038170	0.029405	0.039161	0.031898	0.033830	0.036462	0.059193	0.072336	0.041953	0.070315	0.087141	-0.016930	-0.004708	0.125312	0.204168	0.203046	0.111495	-0.125432	-0.094610	-0.017334	0.239894	0.051983	-0.071446	0.133625	0.060635	0.107483	0.041898	0.168618
new_deaths_smoothed_per_million	0.095372	0.114138	0.118265	0.103195	0.147183	0.151781	0.580378	0.573209	0.696430	0.627766	0.761659	1.000000	0.111029	0.188483	0.493884	0.258051	0.585551	0.088153	0.116361	0.077859	0.128290	0.139507	0.116111	0.224733	0.215499	0.153056	0.257801	0.352966	-0.049257	0.040672	0.053856	0.044109	0.044128	0.050147	0.080723	0.096940	0.058043	0.092980	0.116187	-0.021857	-0.005661	0.162006	0.264513	0.263256	0.145045	-0.162764	-0.124260	-0.022725	0.310304	0.066786	-0.092489	0.172452	0.078847	0.139706	0.050747	0.224186
reproduction_rate	-0.053677	-0.051484	-0.053868	-0.059426	-0.058144	-0.061976	0.113436	0.161570	0.172021	0.113382	0.095104	0.111029	1.000000	0.038855	0.091811	0.049207	0.098755	0.025354	0.022764	0.017967	0.026981	0.074027	0.050926	0.127212	0.113066	0.080627	0.134845	0.279054	-0.001919	-0.032688	-0.032454	-0.029463	-0.032368	-0.034495	-0.024869	-0.026788	-0.025987	-0.056890	0.418368	-0.042066	-0.022857	0.376137	0.294493	0.281492	0.180238	-0.011607	0.127363	0.052727	0.237481	0.215312	0.071026	0.172320	0.333756	0.357612	-0.039500	0.125472
icu_patients	0.167050	0.207915	0.212243	0.141831	0.153560	0.156295	0.189610	0.162670	0.192666	0.209748	0.147454	0.188483	0.038855	1.000000	0.458657	0.935068	0.274910	0.057584	0.024722	0.344632	0.083035	0.693271	0.678932	0.124732	0.082291	0.723640	0.104286	0.047774	-0.010850	0.069731	0.087829	0.077317	0.074826	0.096462	0.048609	0.060465	0.033312	0.049908	0.072597	0.008329	-0.012730	0.108314	0.152195	0.154094	0.146779	-0.042952	-0.068656	0.025804	0.143981	0.025479	-0.070677	0.053769	0.062059	0.101677	0.002655	0.124600
icu_patients_per_million	0.044366	0.064766	0.065476	0.037020	0.054363	0.054274	0.379739	0.380001	0.453811	0.394161	0.384704	0.493884	0.091811	0.458657	1.000000	0.482915	0.707177	0.174015	0.195108	0.164129	0.207849	0.262502	0.221972	0.255339	0.227051	0.290548	0.276112	0.145644	-0.022177	0.018971	0.027037	0.022048	0.020296	0.026192	0.098063	0.111768	0.088027	0.083225	0.144835	-0.027614	-0.020657	0.262480	0.363494	0.372616	0.263075	-0.097072	-0.116509	-0.037622	0.346683	0.091937	-0.155586	0.191935	0.143717	0.213604	0.016448	0.255071
hosp_patients	0.155312	0.198959	0.202595	0.134571	0.150057	0.152396	0.222291	0.204918	0.241222	0.268544	0.201959	0.258051	0.049207	0.935068	0.482915	1.000000	0.441252	0.079062	0.033106	0.329161	0.085865	0.672587	0.637165	0.145622	0.113784	0.691770	0.135677	0.084717	-0.012767	0.063867	0.081964	0.068257	0.069302	0.090230	0.056429	0.072026	0.035746	0.059107	0.089009	0.002732	-0.014845	0.137496	0.194530	0.195155	0.154903	-0.053775	-0.083234	0.000321	0.180451	0.036959	-0.086607	0.067886	0.077994	0.120263	0.008314	0.145460
hosp_patients_per_million	0.019911	0.036703	0.036813	0.017193	0.033229	0.032897	0.379806	0.422492	0.503844	0.407010	0.455957	0.585551	0.098755	0.274910	0.707177	0.441252	1.000000	0.131836	0.166779	0.096579	0.152166	0.197234	0.141853	0.286767	0.311630	0.205804	0.358578	0.213709	-0.022640	0.008063	0.013947	0.009229	0.009232	0.012564	0.084606	0.100773	0.068859	0.080413	0.130002	-0.032953	-0.025507	0.274021	0.376931	0.381943	0.218247	-0.103530	-0.067565	-0.065286	0.374788	0.121144	-0.161093	0.222383	0.137395	0.208631	0.014673	0.286501
weekly_icu_admissions	0.003233	0.003244	0.007140	0.002716	0.000592	0.006190	0.082057	0.050180	0.100595	0.073335	0.042898	0.088153	0.025354	0.057584	0.174015	0.079062	0.131836	1.000000	0.725509	0.220380	0.452138	0.001681	-0.002840	0.008788	0.010118	0.034354	0.045339	0.024463	-0.004593	0.001039	0.001522	0.002628	-0.000898	0.001147	0.034184	0.036544	0.034657	0.027089	0.027721	-0.005597	-0.003803	0.046404	0.067425	0.067026	0.039510	-0.019339	-0.031350	-0.012927	0.080540	0.026038	-0.029040	0.039539	0.029031	0.039938	0.005702	0.008722
weekly_icu_admissions_per_million	-0.001386	-0.002144	0.000651	-0.003176	-0.003276	-0.001283	0.112887	0.074757	0.144452	0.081277	0.068872	0.116361	0.022764	0.024722	0.195108	0.033106	0.166779	0.725509	1.000000	0.140506	0.585200	0.001016	-0.001073	0.045667	0.031036	0.014018	0.071336	0.037657	-0.004930	0.000457	0.000732	0.002406	-0.000671	-0.000036	0.056805	0.060279	0.058159	0.045318	0.027692	-0.007795	-0.003417	0.049389	0.070503	0.069327	0.039891	-0.021763	-0.018713	-0.011976	0.078978	0.032478	-0.032793	0.042805	0.029440	0.044893	-0.001001	0.045602
weekly_hosp_admissions	0.060245	0.064484	0.078322	0.050593	0.028982	0.056241	0.074514	0.053348	0.083918	0.081456	0.034135	0.077859	0.017967	0.344632	0.164129	0.329161	0.096579	0.220380	0.140506	1.000000	0.470875	0.163707	0.249412	0.048597	0.018438	0.260891	0.041091	0.029051	-0.004227	0.024469	0.030287	0.029554	0.026390	0.035353	0.018043	0.022374	0.012907	0.019192	0.026894	0.002160	-0.004970	0.042488	0.058814	0.059004	0.050983	-0.015782	-0.020448	0.009414	0.057261	0.012390	-0.027558	0.021923	0.023308	0.038155	0.001086	0.048545
weekly_hosp_admissions_per_million	0.007456	0.008696	0.013282	0.005673	0.002989	0.009894	0.094312	0.077163	0.134118	0.089775	0.075834	0.128290	0.026981	0.083035	0.207849	0.085865	0.152166	0.452138	0.585200	0.470875	1.000000	0.030735	0.042801	0.046025	0.027161	0.056558	0.060606	0.059068	-0.005786	0.002859	0.004342	0.003761	0.002078	0.004336	0.020414	0.023955	0.017885	0.018123	0.029022	-0.007501	-0.005164	0.065574	0.089623	0.090200	0.043464	-0.021773	-0.007358	-0.005046	0.093810	0.034457	-0.038569	0.057214	0.031422	0.049089	0.000277	0.045947
new_tests	0.176094	0.197580	0.197794	0.145829	0.143001	0.139525	0.184743	0.137356	0.160067	0.206481	0.113285	0.139507	0.074027	0.693271	0.262502	0.672587	0.197234	0.001681	0.001016	0.163707	0.030735	1.000000	0.850537	0.231315	0.259000	0.959910	0.224101	0.051630	-0.006248	0.080641	0.103696	0.083187	0.081093	0.097095	0.096496	0.103842	0.046838	0.071248	0.097247	0.055954	-0.015365	0.120822	0.136676	0.131513	0.143164	-0.035680	-0.032787	0.058241	0.129709	0.059662	-0.042721	0.046531	0.071982	0.118512	-0.009751	0.231107
total_tests	0.210690	0.172913	0.178206	0.163375	0.127968	0.134119	0.195524	0.105801	0.128573	0.196909	0.086355	0.116111	0.050926	0.678932	0.221972	0.637165	0.141853	-0.002840	-0.001073	0.249412	0.042801	0.850537	1.000000	0.233888	0.129574	0.877601	0.149869	0.038318	-0.000818	0.141127	0.173132	0.165012	0.138028	0.164505	0.118158	0.122362	0.073246	0.092846	0.072322	0.052154	-0.011999	0.095470	0.101786	0.097218	0.116549	-0.026701	-0.016536	0.059215	0.094105	0.049853	-0.031025	0.032103	0.055947	0.095064	-0.008914	0.233722
total_tests_per_thousand	0.008818	0.000945	0.001922	-0.002184	-0.009556	-0.008888	0.457347	0.279451	0.335165	0.284645	0.169078	0.224733	0.127212	0.124732	0.255339	0.145622	0.286767	0.008788	0.045667	0.048597	0.046025	0.231315	0.233888	1.000000	0.700227	0.234009	0.808760	0.045558	0.049268	0.025935	0.029039	0.026121	0.018542	0.023061	0.296303	0.226624	0.171590	0.231448	0.082132	-0.044473	0.002842	0.242261	0.234581	0.226684	0.384560	-0.128383	-0.094787	0.077516	0.243980	0.134093	-0.127758	0.121365	0.166853	0.249154	-0.027813	1.000000
new_tests_per_thousand	-0.002867	-0.001406	-0.001699	-0.008226	-0.008984	-0.010318	0.306539	0.248827	0.282043	0.213855	0.171336	0.215499	0.113066	0.082291	0.227051	0.113784	0.311630	0.010118	0.031036	0.018438	0.027161	0.259000	0.129574	0.700227	1.000000	0.195554	0.841009	0.034472	0.022400	0.007601	0.009698	0.004542	0.004217	0.004911	0.173409	0.136969	0.095031	0.140798	0.082602	-0.035225	-0.009117	0.196737	0.203759	0.197701	0.272082	-0.100472	-0.070550	0.042892	0.215084	0.111272	-0.103854	0.114516	0.128829	0.192909	-0.019392	0.700120
new_tests_smoothed	0.184394	0.200244	0.204380	0.152508	0.140609	0.145490	0.201747	0.145248	0.174152	0.227330	0.116431	0.153056	0.080627	0.723640	0.290548	0.691770	0.205804	0.034354	0.014018	0.260891	0.056558	0.959910	0.877601	0.234009	0.195554	1.000000	0.236990	0.053568	-0.000302	0.085584	0.109490	0.090903	0.085717	0.103846	0.100421	0.108343	0.050790	0.075685	0.106010	0.055768	-0.010963	0.143650	0.163709	0.161407	0.163299	-0.043521	-0.040159	0.060796	0.154964	0.069635	-0.053442	0.066067	0.083632	0.136084	-0.010460	0.233772
new_tests_smoothed_per_thousand	-0.003935	-0.003066	-0.002600	-0.010534	-0.013168	-0.013247	0.387508	0.293487	0.348233	0.266208	0.197733	0.257801	0.134845	0.104286	0.276112	0.135677	0.358578	0.045339	0.071336	0.041091	0.060606	0.224101	0.149869	0.808760	0.841009	0.236990	1.000000	0.044084	0.054507	0.008228	0.010767	0.005416	0.004095	0.005433	0.203618	0.163401	0.114343	0.167616	0.095737	-0.044598	0.027929	0.248177	0.257854	0.250638	0.349434	-0.127458	-0.096131	0.058108	0.267484	0.140483	-0.132594	0.144199	0.166006	0.246570	-0.025004	0.808666
positive_rate	-0.031146	-0.021606	-0.021468	-0.026620	-0.011568	-0.012398	0.200742	0.274428	0.324376	0.246467	0.278953	0.352966	0.279054	0.047774	0.145644	0.084717	0.213709	0.024463	0.037657	0.029051	0.059068	0.051630	0.038318	0.045558	0.034472	0.053568	0.044084	1.000000	-0.059293	-0.023491	-0.022768	-0.019281	-0.022766	-0.025715	-0.008491	-0.005893	-0.002592	-0.023333	0.238004	-0.062091	-0.049598	0.172592	0.142323	0.121320	0.038846	-0.010356	-0.008876	0.049870	0.107077	0.075188	0.127191	0.036745	0.147926	0.187903	-0.004562	0.044721
tests_per_case	-0.016797	-0.019654	-0.019736	-0.018823	-0.021013	-0.021468	-0.042170	-0.044086	-0.051688	-0.049904	-0.038170	-0.049257	-0.001919	-0.010850	-0.022177	-0.012767	-0.022640	-0.004593	-0.004930	-0.004227	-0.005786	-0.006248	-0.000818	0.049268	0.022400	-0.000302	0.054507	-0.059293	1.000000	-0.007437	-0.007608	-0.006871	-0.007525	-0.008812	-0.009393	-0.010211	-0.007267	-0.011795	0.016976	-0.019104	0.038058	0.086532	0.071289	0.071439	0.093266	-0.045423	-0.053766	0.006233	0.025387	0.016185	0.005201	0.024104	0.065463	0.074840	0.004192	0.049068
total_vaccinations	0.709946	0.388810	0.392009	0.665703	0.414428	0.434847	0.103211	0.022902	0.028140	0.109736	0.029405	0.040672	-0.032688	0.069731	0.018971	0.063867	0.008063	0.001039	0.000457	0.024469	0.002859	0.080641	0.141127	0.025935	0.007601	0.085584	0.008228	-0.023491	-0.007437	1.000000	0.985054	0.957749	0.875001	0.960024	0.118665	0.122346	0.090418	0.082558	-0.073245	0.311227	-0.010071	-0.036586	-0.012049	-0.012172	-0.006237	-0.015202	-0.051262	-0.028161	-0.006693	-0.011914	-0.001401	-0.020649	-0.085711	-0.047074	-0.002702	0.025837
people_vaccinated	0.716938	0.397605	0.401355	0.677479	0.429076	0.450076	0.123252	0.030287	0.037136	0.134283	0.039161	0.053856	-0.032454	0.087829	0.027037	0.081964	0.013947	0.001522	0.000732	0.030287	0.004342	0.103696	0.173132	0.029039	0.009698	0.109490	0.010767	-0.022768	-0.007608	0.985054	1.000000	0.972234	0.858912	0.943917	0.128722	0.145309	0.099634	0.092726	-0.071000	0.287409	-0.010151	-0.035110	-0.008371	-0.008399	-0.004519	-0.015686	-0.053841	-0.029690	-0.002798	-0.012807	-0.002428	-0.020879	-0.085441	-0.045670	-0.002199	0.028937
people_fully_vaccinated	0.637546	0.328983	0.328814	0.602474	0.352333	0.370088	0.120889	0.026165	0.031701	0.124896	0.031898	0.044109	-0.029463	0.077317	0.022048	0.068257	0.009229	0.002628	0.002406	0.029554	0.003761	0.083187	0.165012	0.026121	0.004542	0.090903	0.005416	-0.019281	-0.006871	0.957749	0.972234	1.000000	0.807367	0.887331	0.139038	0.145626	0.130317	0.093888	-0.064170	0.242055	-0.009298	-0.031113	-0.006861	-0.007080	-0.001097	-0.014860	-0.048160	-0.024715	-0.000799	-0.011158	-0.004413	-0.016593	-0.075702	-0.039920	-0.001935	0.026033
new_vaccinations	0.699287	0.422973	0.425698	0.653199	0.456267	0.467670	0.094056	0.025943	0.030964	0.101472	0.033830	0.044128	-0.032368	0.074826	0.020296	0.069302	0.009232	-0.000898	-0.000671	0.026390	0.002078	0.081093	0.138028	0.018542	0.004217	0.085717	0.004095	-0.022766	-0.007525	0.875001	0.858912	0.807367	1.000000	0.899155	0.089690	0.095552	0.065368	0.072363	-0.074309	0.318310	-0.010010	-0.038497	-0.014155	-0.014160	-0.009345	-0.013891	-0.051031	-0.028608	-0.008240	-0.012932	0.001317	-0.022176	-0.087618	-0.049239	-0.002707	0.018442
new_vaccinations_smoothed	0.766562	0.454275	0.463595	0.716121	0.487689	0.511886	0.107851	0.028801	0.036003	0.115260	0.036462	0.050147	-0.034495	0.096462	0.026192	0.090230	0.012564	0.001147	-0.000036	0.035353	0.004336	0.097095	0.164505	0.023061	0.004911	0.103846	0.005433	-0.025715	-0.008812	0.960024	0.943917	0.887331	0.899155	1.000000	0.100958	0.107417	0.073796	0.084578	-0.077143	0.352143	-0.011321	-0.036704	-0.011687	-0.012751	-0.008188	-0.018000	-0.055207	-0.028498	-0.008931	-0.007200	-0.002696	-0.020466	-0.092898	-0.050473	-0.003393	0.022941
total_vaccinations_per_hundred	0.061655	0.025148	0.026080	0.053589	0.027582	0.029955	0.250308	0.128378	0.152240	0.164580	0.059193	0.080723	-0.024869	0.048609	0.098063	0.056429	0.084606	0.034184	0.056805	0.018043	0.020414	0.096496	0.118158	0.296303	0.173409	0.100421	0.203618	-0.008491	-0.009393	0.118665	0.128722	0.139038	0.089690	0.100958	1.000000	0.918229	0.892749	0.633313	-0.027286	-0.005554	0.033330	-0.000745	0.028840	0.024467	0.068694	-0.051714	-0.080507	-0.010601	0.049559	0.009010	-0.061014	0.002118	0.038295	-0.006267	-0.011414	0.296202
people_vaccinated_per_hundred	0.069220	0.029821	0.030955	0.062107	0.034202	0.036991	0.261211	0.135856	0.158618	0.193320	0.072336	0.096940	-0.026788	0.060465	0.111768	0.072026	0.100773	0.036544	0.060279	0.022374	0.023955	0.103842	0.122362	0.226624	0.136969	0.108343	0.163401	-0.005893	-0.010211	0.122346	0.145309	0.145626	0.095552	0.107417	0.918229	1.000000	0.882632	0.634031	-0.023058	-0.006301	0.037979	-0.001204	0.046130	0.041364	0.054583	-0.052676	-0.095189	-0.032465	0.065581	0.000998	-0.066005	0.010227	0.036722	-0.013074	-0.010258	0.226494
people_fully_vaccinated_per_hundred	0.045063	0.015983	0.016457	0.038132	0.017284	0.018918	0.199877	0.093364	0.112353	0.123952	0.041953	0.058043	-0.025987	0.033312	0.088027	0.035746	0.068859	0.034657	0.058159	0.012907	0.017885	0.046838	0.073246	0.171590	0.095031	0.050790	0.114343	-0.002592	-0.007267	0.090418	0.099634	0.130317	0.065368	0.073796	0.892749	0.882632	1.000000	0.508073	-0.026437	-0.005842	0.032462	-0.009867	0.028714	0.023995	0.035012	-0.037047	-0.071317	-0.029801	0.046449	0.000693	-0.049580	0.006791	0.031069	-0.014912	-0.008141	0.171501
new_vaccinations_smoothed_per_million	0.048157	0.018978	0.020343	0.039971	0.020900	0.023029	0.238136	0.139727	0.166602	0.155402	0.070315	0.092980	-0.056890	0.049908	0.083225	0.059107	0.080413	0.027089	0.045318	0.019192	0.018123	0.071248	0.092846	0.231448	0.140798	0.075685	0.167616	-0.023333	-0.011795	0.082558	0.092726	0.093888	0.072363	0.084578	0.633313	0.634031	0.508073	1.000000	-0.067837	-0.014540	0.082324	-0.068941	-0.009645	-0.013092	0.064651	-0.073926	-0.136471	-0.024017	0.024590	-0.033433	-0.080367	-0.003140	0.045405	-0.085219	-0.014338	0.231352
stringency_index	-0.143389	-0.158905	-0.159214	-0.160678	-0.166023	-0.169794	0.047408	0.060453	0.076521	0.067364	0.087141	0.116187	0.418368	0.072597	0.144835	0.089009	0.130002	0.027721	0.027692	0.026894	0.029022	0.097247	0.072322	0.082132	0.082602	0.106010	0.095737	0.238004	0.016976	-0.073245	-0.071000	-0.064170	-0.074309	-0.077143	-0.027286	-0.023058	-0.026437	-0.067837	1.000000	-0.194006	0.017389	0.289722	0.161853	0.140006	0.137627	-0.042154	0.159565	0.136867	0.124935	0.208290	0.138666	0.088965	0.329506	0.316832	0.026320	0.079944
population	0.603536	0.661523	0.664703	0.640373	0.679298	0.695507	-0.032864	-0.029948	-0.034918	-0.017309	-0.016930	-0.021857	-0.042066	0.008329	-0.027614	0.002732	-0.032953	-0.005597	-0.007795	0.002160	-0.007501	0.055954	0.052154	-0.044473	-0.035225	0.055768	-0.044598	-0.062091	-0.019104	0.311227	0.287409	0.242055	0.318310	0.352143	-0.005554	-0.006301	-0.005842	-0.014540	-0.194006	1.000000	-0.026434	-0.110267	-0.063992	-0.066128	-0.070108	-0.021541	-0.106414	-0.075626	-0.067073	-0.016264	0.032874	-0.061791	-0.235857	-0.147653	0.004737	-0.044799

Data Scientist Capstone¶

By Marwan Saeed Alsharabbi¶

COVID-19 Analysis ,visualization & Prediction¶

Introduction

Step 1: Select a real-world dataset¶

Data Sources:¶

License:¶

Authors:¶

Step 2: Questions¶

Step 3: Problems and Modeling¶

1- Problem Question :¶

2- Problem Question:¶

Importing Libraries¶

In this link, every execution process pulls the new and updated data from the link¶

Step 2: Perform data preparation & Cleaning¶

Numerical Features¶

Categorical Features¶

Analysis preparation

Step 3: Perform exploratory Analysis & Visualization¶

Loading the cleaned Data and Exploring the histogram of the data looks like¶

It appears that each column contains values of a specific data type. You can view statistical information for numerical columns (mean, standard deviation, minimum/maximum values, and the number of non-empty values) using the .describe method.¶

Business Questions¶

Data Understanding¶

Question#1¶

How the many total population in each location by continents from our datase¶

Question#1¶

How the many total population in each location by continents from our datase¶

Question#2¶

The 10 top population total in each location by continents from our dataset¶

The 10 top population total in each location by continent 'Africa from our dataset¶

Create a data frame showing the total population of each continent¶

Question#3¶

Show countries in Asia,Europe and North America the total_cases and total_deaths,new_cases,total_tests, total_vaccinations by mean, and max¶

Question#4¶

Let's see the speed of transmission of the Corona virus between countries on the map .¶

Worldwide spread¶

We can see trend covid-19 moving to China -> Europe -> US¶

We can see trend covid-19 moving to China -> Europe -> US on map¶

Question#5¶

Let's see number of total_cases,total_deaths,total_deaths_per_million,test per confirmed(%) on map.¶

COVID-19 maps¶

Let's see number of confirmed cases on map.¶

Let's see number of deaths on map.¶

Let's see number of total deaths per million on map.¶

We can see that south,north America and europe has the most number of total deaths per million¶

Question#5¶

Top 15 countries for the total_cases,total_deaths,total_deaths_per_million,total_tests,people_fully_vaccinated and total_vaccinations on plot_hbar and Visulizing Treemaps¶

Top 15 countries¶

Visulizing Treemaps¶

Line Plot function¶

Question#6¶

How many the New Deaths Smoothed day by day in continents¶

Question#7¶

How many the new vaccinations smoothed day by day in continents¶

Question#8¶

How many the New Tests Smoothed day by day in continents¶

Question#8¶

How many the positive_rate day by day in continents¶

Test population coverage¶

Question#9¶

find some gdp_per_capita and new_cases clusters over countries¶

Question#10¶

find some new_deaths_smoothed_per_million, handwashing_facilities and extreme_poverty clusters over countries¶

Question#11¶

find some new_deaths_smoothed_per_million, aged_70_older and population_density clusters over countries¶

Question#12¶

find some new_deaths_smoothed_per_million, life_expectancy and hospital_beds_per_thousand clusters over countries¶

Stringency Index and death rate correlation¶

Modeling

Correlation Analysis¶

Linear Regression-Forecast

k-nearest neighbors(KNN) algorithm

I will create a model that can predict the risk for the Case Mortality Ratio of a Country utilizing its Life Expectancy, Percentage of Population over 65, and Percentage of diabetes_prevalence and cardiovasc_death_rate ? ¶

Correlation Analysis¶

We will be using the diabetes, cardiovascular health, percent of poplation above 70 and any other data we find to be the most useful to see if we can get better results with these features.¶

Now we will split our data for the Machine Learning Algorithm using the High Risk Category as our target and Life_Expectancy,icu_patients ,diabetes_prevalence, and aged_65_older as features¶

It looks like despite our initial reservations that KNN was able to get a decent accuracy of 90.19 %¶

Let's test which k value gets us our best accuracy.¶

Interestingly a slightly better classification of 90.518% with k =7.¶

Now we will try to test all the features we currently have and select through a greedy algorithm the best features utilizing KNN and all K-Ranges between 1 and 7¶